SlideShare ist ein Scribd-Unternehmen logo
1 von 27
Downloaden Sie, um offline zu lesen
Pooling?
Max Pool
Avg Pool
(NOT) All about that Pooling
in Image Processing
Today
Pooling Operations
Pooling Analysis
What is Pooling/Subsampling for?
Obj : Transform the "joint feature representation” into a new, more usable
Const
- discarding irrelevant detail
=> Invariance to changes in position/lighting, Robust to clutter, Compactness
of representation...
A Theoretical Analysis of Feature Pooling in Visual Recognition (2010)
Pooling Operations
This is the point
Const
- discarding irrelevant detail
Pros
Increasing Receptive Field
Decrease Model Size
Remove Noise
Translation Invariance
Cons
Lose Details
Lack (or NOT) of Equivariance
Pooling Operations
for TLDR;
StaticLearnable
Universal
Particular
Max Pooling
Avg Pooling
Fractional Pooling
LP Pooling
Wavelet Pooling
Softmax Pooling
Stochastic Pooling
Blur Pooling
Orderable Pooling
Global Average Pooling
Strided Convolution
Mixed, Gated, Tree Pooling
Local Importance Pooling
Detail-Preserving Pooling
Sensitive
Insensitive
Pooling Operations
Global Feature Guided Local Pooling
Spatial Pyramid Pooling
for TLDR;
Sensitive
Insensitive
Pooling Operations
Response Sensitivity
Someone, Orderable/Ranking/Attention
Max Pooling
Global Max Pooling
Softmax Pooling
Orderable Pooling
Mixed, Gated, Tree Pooling
Local Importance Pooling
Detail-Preserving Pooling
Spatial Pyramid Pooling
Fractional Pooling
Stochastic Pooling
Strided Convolution
Avg Pooling
Wavelet Pooling
LP Pooling
Global Feature Guided Local Pooling
Blur Pooling
시작하기 전 TMI
CNN - Cat neuron response experiment (1962)
Average Pooling - Lenet (1998) : Subsampling
Max Pooling - Monkey neuron response exp (1999) -> DBN (2006)
-> Hand gesture recognition with cnn (2010)
Pooling Operations
Main Pooling Papers
Average Pooling
Lenet’s Subsampling [2]
Max Pooling
Similar to Neuron’s (at least monkey) response than avg [1]
LP Pooling
Average Pool - Max Pool. With hyperparameter, we can get avg/weighted/max pooling
Spatial Pyramid Pooling
Overcome CNN’s fixed output (GAP), Diversiform Receptive Field
Strided Convolution
Trainable Pooling
Pooling Operations
Average Pooling vs Max Pooling
Pooling Operations
Feature
Use all information with sum
> Pros
Backpropagation to all response
> Cons
Not robust to noise
Feature
Use highest value
> Pros
Robust to Noise
> Cons
Details are removed
vs
Suitable for Sparse Information
- Image Classification
Suitable for Dense Information
- NLP [below 1]
Avg / Response Insensitive Max / Response Sensitive
Start with 90s
Average Pooling / Max Pooling Balancing
- Transformable 2012
Pooling Operations
Convolutional Neural Networks Applied to House Numbers Digit Classification (2012)
LP Pool
by hyperparameter ‘p’, LP Pool is controllable from Avg(p=1) to Max(p=inf)
- Exp on Lenet Base
*SS: Single Stage, MS : Multi stage (Depth)
Average Pooling / Max Pooling Balancing
- Transformable 2017
Pooling Operations
DCASE 2017 SUBMISSION: MULTIPLE INSTANCE LEARNING FOR SOUND EVENT DETECTION (2017)
adaptive pooling operators for weakly labeled sound event detection (2018)
Softmax Pool
( Auto Pool )
by hyperparameter ‘a’, controllable from Avg(a=0), Softmax(a=1) to
Max(a=inf)
* RAP : Restricted Auto Pool (add regularizer for moving near 0), CAP : Contrainted Auto Pool ( value const for moving near 0 )
* Strong - time-varying label / Weak - No time labeled
- CNN based voice-spectrogram cls
Average Pooling / Max Pooling Balancing
- Hybrid 2015
Pooling Operations
Generalizing Pooling Functions in Convolutional Neural Networks:Mixed, Gated, and Tree (2015)
Mix/Gate Pool
- Maybe Exp on (pool 2) Alexnet Base
* Baseline : Max pool
+ Better Result & More Robust on transition
‘a’ parameter mix avg/max response
Average Pooling / Max Pooling Balancing
- Transformable + Hybrid 2019
Pooling Operations
Global Feature Guided Local Pooling (2019)
Global Feature Guided Local Pooling
- Softmax Pooling인데, GAP-FC로 parameter 데이터 마다 조정!
- More Depth, Pooling activated AVG/MAX
*trainable
`lambda` : 0, ‘rho’ :0 -> Avg
`lambda` : inf, ‘rho’ :0 -> Max
`lambda` : -inf, ‘rho’ :0 -> Min
Response Position
- Pooling Activation is Different by Cls (Imagenet)
(Max Pooling) Only Response Sensitive!
- Use Nth Max Responses 2016 - 2019
Pooling Operations
Rank-based pooling for deep convolutional neural networks (2016)
Ordinal Pooling (2019)
Ordinal Pooling
Weighting by Response Value
Notable thing
- At First Pooling, Closed to Avg. At Last, Close to Max
* baseline :Modified Lenet Avg/GAP - MNIST
Detail Please
- Detail reinforce 2018
Pooling Operations
Rapid, Detail-Preserving Image Downscaling (2016)
Detail-Preserving Pooling in Deep Networks (2018)
Detail Please
- Detail reinforce 2018
Pooling Operations
Rapid, Detail-Preserving Image Downscaling (2016)
Detail-Preserving Pooling in Deep Networks (2018)
(Assum) Original Image - Normed Downscaled Image == Details
Detail Preserving Pooling
*https://github.com/Tensor46/TensorMONK/
Blurring Image
Detail Reflection
* Trainable
Detail Please
- Detail reinforce 2019
Pooling Operations
LIP: Local Importance-based Pooling (2019)
Local Importance Pooling
Calculate Pixel Importance
(Gate)
Reinforce
Response by Gate
LIP-AVG-Strided
CAM - 코알라
Hmm… Multiple Pooling
- Diversity Bags
Pooling Operations
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories (2006)
Spatial Pyramid Pooling in Deep ConvolutionalNetworks for Visual Recognition (2014)
Spatial Pyramid Pooling
GAP
Training, Training, Training
- NONO Pooling! 2014
Pooling Operations
Striving for simplicity, the all convolutional net (2014)
Strided Convolution
* BUT! FishNet reports
Strided Conv is worse
than Max Pool
* Stride Convs can’t
approximate MaxPool
(Ordinal)
Jackpot plz
- Stochastic 2013
Pooling Operations
Stochastic Pooling for Regularization of Deep Convolutional Neural Networks (2013)
Stochastic Pooling
- Train time : Stochastically Pool
- Test time : Weight Pool
Why only Integer division?
- Rebellion of root 2015
Pooling Operations
Fractional Max Pooling 2015
Fractional Max-Pooling
- Random Kernel Size for Max pooling -
for achieving root size downsample
* In = 25, Out =18
(root 2) = 1.414 / 25/18 = 1.388
Pooling has a WEAKNESS
- Avoiding Kryptonium 2019
Pooling Operations
Making Convolutional Networks Shift-Invariant Again 2019
https://richzhang.github.io/antialiased-cnns/
* Data Aug was removed
Blur Pool
Pooling has a WEAKNESS
- Failed KING 2017
Pooling Operations
CapsuleNet 2017
* Notable, “Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition (ICANN 2010)
- Exp shows overlapping drops accuracy
* By Contrast, “AlexNet (2012)” Report overlapping is helpful for prevent overfitting
Family Tree
Max Pooling Avg Pooling
Spatial Pyramid Pool
- 좀 더 다양하게 볼래
LP/Softmax Pool
- 왔다 갔다할 수 있음!
족보 없음
Stochastic Pooling
- 아무나 고를래!
Wavelet Pooling
- Edge는 무조건 중요!
Ordinal Pool
- Flex 여러개 봄
Mixed Pool
- 동시에 둘다 볼래
Strided Convolution
- 요즘은 러닝 시대
Rank Pool
- 여러개 볼래
Blur Pool
- Blurring하면 더 좋아짐!
Fractional Pooling
- 커널 크기 랜덤할래
Global Pool
- 다 묻고 하나만 가!
Detail Preserve Pool
- Detail 어디감
Local Importance Pool
- More Trainable
Robust Attention Pool
- GMP도 Trainable 하게
Global Feature Guided Local Pool
- Input에 따라 avg/max 조절할래
( Trainable LP )
Evaluation of Pooling Operations in Convolutional Architectures for Object
Recognition (2010)
- Overlapping pool drops accuracy
A Theoretical Analysis of Feature Pooling in Visual Recognition (2010)
- Proof if Response is sparse, max pooling is better than avg pooling
Pooling is neither necessary nor sufficient for appropriate deformation stability
in CNNS (2018)
Ask the locals: multi-way local pooling for image recognition (2011)
Signal recovery from Pooling Representations (2014)
stats385
Emergence of Invariance and Disentanglement in Deep Representations
(2018)
Quantifying Translation-Invariance in Convolutional Neural Networks (2017)
A Mathematical Theory of Deep Convolutional Neural Networks for Feature
Extraction (2017)
Learning to Linearize Under Uncertainty (2015)
Pooling Analysis

Weitere ähnliche Inhalte

Was ist angesagt?

Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Gaurav Mittal
 
Photo-realistic Single Image Super-resolution using a Generative Adversarial ...
Photo-realistic Single Image Super-resolution using a Generative Adversarial ...Photo-realistic Single Image Super-resolution using a Generative Adversarial ...
Photo-realistic Single Image Super-resolution using a Generative Adversarial ...Hansol Kang
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsKasun Chinthaka Piyarathna
 
Image segmentation ppt
Image segmentation pptImage segmentation ppt
Image segmentation pptGichelle Amon
 
Deep Reinforcement Learning
Deep Reinforcement LearningDeep Reinforcement Learning
Deep Reinforcement LearningUsman Qayyum
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningJunaid Bhat
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnBenjamin Bengfort
 
Brief Introduction to Boltzmann Machine
Brief Introduction to Boltzmann MachineBrief Introduction to Boltzmann Machine
Brief Introduction to Boltzmann MachineArunabha Saha
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningMohamed Loey
 
Neural network & its applications
Neural network & its applications Neural network & its applications
Neural network & its applications Ahmed_hashmi
 
Optimization for Deep Learning
Optimization for Deep LearningOptimization for Deep Learning
Optimization for Deep LearningSebastian Ruder
 
Chapter10 image segmentation
Chapter10 image segmentationChapter10 image segmentation
Chapter10 image segmentationasodariyabhavesh
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networksSi Haem
 
Introduction to Neural Networks
Introduction to Neural NetworksIntroduction to Neural Networks
Introduction to Neural NetworksDatabricks
 
A Deep Journey into Super-resolution
A Deep Journey into Super-resolutionA Deep Journey into Super-resolution
A Deep Journey into Super-resolutionRonak Mehta
 
Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Suraj Aavula
 

Was ist angesagt? (20)

Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)
 
Photo-realistic Single Image Super-resolution using a Generative Adversarial ...
Photo-realistic Single Image Super-resolution using a Generative Adversarial ...Photo-realistic Single Image Super-resolution using a Generative Adversarial ...
Photo-realistic Single Image Super-resolution using a Generative Adversarial ...
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its Applications
 
Transfer Learning
Transfer LearningTransfer Learning
Transfer Learning
 
Image segmentation ppt
Image segmentation pptImage segmentation ppt
Image segmentation ppt
 
Deep Reinforcement Learning
Deep Reinforcement LearningDeep Reinforcement Learning
Deep Reinforcement Learning
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
IMAGE SEGMENTATION.
IMAGE SEGMENTATION.IMAGE SEGMENTATION.
IMAGE SEGMENTATION.
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-Learn
 
Brief Introduction to Boltzmann Machine
Brief Introduction to Boltzmann MachineBrief Introduction to Boltzmann Machine
Brief Introduction to Boltzmann Machine
 
CNN Tutorial
CNN TutorialCNN Tutorial
CNN Tutorial
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep Learning
 
Mathematical tools in dip
Mathematical tools in dipMathematical tools in dip
Mathematical tools in dip
 
Neural network & its applications
Neural network & its applications Neural network & its applications
Neural network & its applications
 
Optimization for Deep Learning
Optimization for Deep LearningOptimization for Deep Learning
Optimization for Deep Learning
 
Chapter10 image segmentation
Chapter10 image segmentationChapter10 image segmentation
Chapter10 image segmentation
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networks
 
Introduction to Neural Networks
Introduction to Neural NetworksIntroduction to Neural Networks
Introduction to Neural Networks
 
A Deep Journey into Super-resolution
A Deep Journey into Super-resolutionA Deep Journey into Super-resolution
A Deep Journey into Super-resolution
 
Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)
 

Ähnlich wie All about that pooling

High-Performance Physics Solver Design for Next Generation Consoles
High-Performance Physics Solver Design for Next Generation ConsolesHigh-Performance Physics Solver Design for Next Generation Consoles
High-Performance Physics Solver Design for Next Generation ConsolesSlide_N
 
Tensor Field Network (and other ConvNet Generalisations)
Tensor Field Network (and other ConvNet Generalisations)Tensor Field Network (and other ConvNet Generalisations)
Tensor Field Network (and other ConvNet Generalisations)Peng Cheng
 
Resource Scheduling using Apache Mesos in Cloud Native Environments
Resource Scheduling using Apache Mesos in Cloud Native EnvironmentsResource Scheduling using Apache Mesos in Cloud Native Environments
Resource Scheduling using Apache Mesos in Cloud Native EnvironmentsSharma Podila
 
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...KAIST
 
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...KAIST
 
Unexpected Challenges in Large Scale Machine Learning by Charles Parker
 Unexpected Challenges in Large Scale Machine Learning by Charles Parker Unexpected Challenges in Large Scale Machine Learning by Charles Parker
Unexpected Challenges in Large Scale Machine Learning by Charles ParkerBigMine
 
[RakutenTechConf2014] [D-4] The next step of LeoFS and Introducing NewDB Project
[RakutenTechConf2014] [D-4] The next step of LeoFS and Introducing NewDB Project[RakutenTechConf2014] [D-4] The next step of LeoFS and Introducing NewDB Project
[RakutenTechConf2014] [D-4] The next step of LeoFS and Introducing NewDB ProjectRakuten Group, Inc.
 
Intro to SnappyData Webinar
Intro to SnappyData WebinarIntro to SnappyData Webinar
Intro to SnappyData WebinarSnappyData
 
2014-08-14 Alpine Innovation to Spark
2014-08-14 Alpine Innovation to Spark2014-08-14 Alpine Innovation to Spark
2014-08-14 Alpine Innovation to SparkDB Tsai
 
Public Cloud Performance Measurement Report
Public Cloud Performance Measurement ReportPublic Cloud Performance Measurement Report
Public Cloud Performance Measurement ReportStorPool Storage
 
Big Data Real Time Analytics - A Facebook Case Study
Big Data Real Time Analytics - A Facebook Case StudyBig Data Real Time Analytics - A Facebook Case Study
Big Data Real Time Analytics - A Facebook Case StudyNati Shalom
 
Routing in Dense Topologies - What's all the Fuss?
Routing in Dense Topologies - What's all the Fuss?Routing in Dense Topologies - What's all the Fuss?
Routing in Dense Topologies - What's all the Fuss?APNIC
 
GeoSpatially enabling your Spark and Accumulo clusters with LocationTech
GeoSpatially enabling your Spark and Accumulo clusters with LocationTechGeoSpatially enabling your Spark and Accumulo clusters with LocationTech
GeoSpatially enabling your Spark and Accumulo clusters with LocationTechRob Emanuele
 
RNNs for Recommendations and Personalization
RNNs for Recommendations and PersonalizationRNNs for Recommendations and Personalization
RNNs for Recommendations and PersonalizationNick Pentreath
 
PIT Overload Analysis in Content Centric Networks - Slides ICN '13
PIT Overload Analysis in Content Centric Networks - Slides ICN '13PIT Overload Analysis in Content Centric Networks - Slides ICN '13
PIT Overload Analysis in Content Centric Networks - Slides ICN '13Matteo Virgilio
 
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...Yan Xu
 
Magnet Shuffle Service: Push-based Shuffle at LinkedIn
Magnet Shuffle Service: Push-based Shuffle at LinkedInMagnet Shuffle Service: Push-based Shuffle at LinkedIn
Magnet Shuffle Service: Push-based Shuffle at LinkedInDatabricks
 
Scalable Machine Learning: The Role of Stratified Data Sharding
Scalable Machine Learning: The Role of Stratified Data ShardingScalable Machine Learning: The Role of Stratified Data Sharding
Scalable Machine Learning: The Role of Stratified Data Shardinginside-BigData.com
 
SnappyData Overview Slidedeck for Big Data Bellevue
SnappyData Overview Slidedeck for Big Data Bellevue SnappyData Overview Slidedeck for Big Data Bellevue
SnappyData Overview Slidedeck for Big Data Bellevue SnappyData
 

Ähnlich wie All about that pooling (20)

High-Performance Physics Solver Design for Next Generation Consoles
High-Performance Physics Solver Design for Next Generation ConsolesHigh-Performance Physics Solver Design for Next Generation Consoles
High-Performance Physics Solver Design for Next Generation Consoles
 
Tensor Field Network (and other ConvNet Generalisations)
Tensor Field Network (and other ConvNet Generalisations)Tensor Field Network (and other ConvNet Generalisations)
Tensor Field Network (and other ConvNet Generalisations)
 
Blue Gene Active Storage
Blue Gene Active StorageBlue Gene Active Storage
Blue Gene Active Storage
 
Resource Scheduling using Apache Mesos in Cloud Native Environments
Resource Scheduling using Apache Mesos in Cloud Native EnvironmentsResource Scheduling using Apache Mesos in Cloud Native Environments
Resource Scheduling using Apache Mesos in Cloud Native Environments
 
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
 
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
[AAAI2018] Multispectral Transfer Network: Unsupervised Depth Estimation for ...
 
Unexpected Challenges in Large Scale Machine Learning by Charles Parker
 Unexpected Challenges in Large Scale Machine Learning by Charles Parker Unexpected Challenges in Large Scale Machine Learning by Charles Parker
Unexpected Challenges in Large Scale Machine Learning by Charles Parker
 
[RakutenTechConf2014] [D-4] The next step of LeoFS and Introducing NewDB Project
[RakutenTechConf2014] [D-4] The next step of LeoFS and Introducing NewDB Project[RakutenTechConf2014] [D-4] The next step of LeoFS and Introducing NewDB Project
[RakutenTechConf2014] [D-4] The next step of LeoFS and Introducing NewDB Project
 
Intro to SnappyData Webinar
Intro to SnappyData WebinarIntro to SnappyData Webinar
Intro to SnappyData Webinar
 
2014-08-14 Alpine Innovation to Spark
2014-08-14 Alpine Innovation to Spark2014-08-14 Alpine Innovation to Spark
2014-08-14 Alpine Innovation to Spark
 
Public Cloud Performance Measurement Report
Public Cloud Performance Measurement ReportPublic Cloud Performance Measurement Report
Public Cloud Performance Measurement Report
 
Big Data Real Time Analytics - A Facebook Case Study
Big Data Real Time Analytics - A Facebook Case StudyBig Data Real Time Analytics - A Facebook Case Study
Big Data Real Time Analytics - A Facebook Case Study
 
Routing in Dense Topologies - What's all the Fuss?
Routing in Dense Topologies - What's all the Fuss?Routing in Dense Topologies - What's all the Fuss?
Routing in Dense Topologies - What's all the Fuss?
 
GeoSpatially enabling your Spark and Accumulo clusters with LocationTech
GeoSpatially enabling your Spark and Accumulo clusters with LocationTechGeoSpatially enabling your Spark and Accumulo clusters with LocationTech
GeoSpatially enabling your Spark and Accumulo clusters with LocationTech
 
RNNs for Recommendations and Personalization
RNNs for Recommendations and PersonalizationRNNs for Recommendations and Personalization
RNNs for Recommendations and Personalization
 
PIT Overload Analysis in Content Centric Networks - Slides ICN '13
PIT Overload Analysis in Content Centric Networks - Slides ICN '13PIT Overload Analysis in Content Centric Networks - Slides ICN '13
PIT Overload Analysis in Content Centric Networks - Slides ICN '13
 
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
 
Magnet Shuffle Service: Push-based Shuffle at LinkedIn
Magnet Shuffle Service: Push-based Shuffle at LinkedInMagnet Shuffle Service: Push-based Shuffle at LinkedIn
Magnet Shuffle Service: Push-based Shuffle at LinkedIn
 
Scalable Machine Learning: The Role of Stratified Data Sharding
Scalable Machine Learning: The Role of Stratified Data ShardingScalable Machine Learning: The Role of Stratified Data Sharding
Scalable Machine Learning: The Role of Stratified Data Sharding
 
SnappyData Overview Slidedeck for Big Data Bellevue
SnappyData Overview Slidedeck for Big Data Bellevue SnappyData Overview Slidedeck for Big Data Bellevue
SnappyData Overview Slidedeck for Big Data Bellevue
 

Mehr von Dong Heon Cho

Forward-Forward Algorithm
Forward-Forward AlgorithmForward-Forward Algorithm
Forward-Forward AlgorithmDong Heon Cho
 
Neural Radiance Field
Neural Radiance FieldNeural Radiance Field
Neural Radiance FieldDong Heon Cho
 
2020 > Self supervised learning
2020 > Self supervised learning2020 > Self supervised learning
2020 > Self supervised learningDong Heon Cho
 
Background elimination review
Background elimination reviewBackground elimination review
Background elimination reviewDong Heon Cho
 
Transparent Latent GAN
Transparent Latent GANTransparent Latent GAN
Transparent Latent GANDong Heon Cho
 
Multi object Deep reinforcement learning
Multi object Deep reinforcement learningMulti object Deep reinforcement learning
Multi object Deep reinforcement learningDong Heon Cho
 
Multi agent reinforcement learning for sequential social dilemmas
Multi agent reinforcement learning for sequential social dilemmasMulti agent reinforcement learning for sequential social dilemmas
Multi agent reinforcement learning for sequential social dilemmasDong Heon Cho
 
Hybrid reward architecture
Hybrid reward architectureHybrid reward architecture
Hybrid reward architectureDong Heon Cho
 
Use Jupyter notebook guide in 5 minutes
Use Jupyter notebook guide in 5 minutesUse Jupyter notebook guide in 5 minutes
Use Jupyter notebook guide in 5 minutesDong Heon Cho
 
AlexNet and so on...
AlexNet and so on...AlexNet and so on...
AlexNet and so on...Dong Heon Cho
 
Deep Learning AtoC with Image Perspective
Deep Learning AtoC with Image PerspectiveDeep Learning AtoC with Image Perspective
Deep Learning AtoC with Image PerspectiveDong Heon Cho
 
How can we train with few data
How can we train with few dataHow can we train with few data
How can we train with few dataDong Heon Cho
 
Domain adaptation gan
Domain adaptation ganDomain adaptation gan
Domain adaptation ganDong Heon Cho
 
Dense sparse-dense training for dnn and Other Models
Dense sparse-dense training for dnn and Other ModelsDense sparse-dense training for dnn and Other Models
Dense sparse-dense training for dnn and Other ModelsDong Heon Cho
 

Mehr von Dong Heon Cho (20)

Forward-Forward Algorithm
Forward-Forward AlgorithmForward-Forward Algorithm
Forward-Forward Algorithm
 
What is Texture.pdf
What is Texture.pdfWhat is Texture.pdf
What is Texture.pdf
 
BADGE
BADGEBADGE
BADGE
 
Neural Radiance Field
Neural Radiance FieldNeural Radiance Field
Neural Radiance Field
 
2020 > Self supervised learning
2020 > Self supervised learning2020 > Self supervised learning
2020 > Self supervised learning
 
Background elimination review
Background elimination reviewBackground elimination review
Background elimination review
 
Transparent Latent GAN
Transparent Latent GANTransparent Latent GAN
Transparent Latent GAN
 
Image matting atoc
Image matting atocImage matting atoc
Image matting atoc
 
Multi object Deep reinforcement learning
Multi object Deep reinforcement learningMulti object Deep reinforcement learning
Multi object Deep reinforcement learning
 
Multi agent reinforcement learning for sequential social dilemmas
Multi agent reinforcement learning for sequential social dilemmasMulti agent reinforcement learning for sequential social dilemmas
Multi agent reinforcement learning for sequential social dilemmas
 
Multi agent System
Multi agent SystemMulti agent System
Multi agent System
 
Hybrid reward architecture
Hybrid reward architectureHybrid reward architecture
Hybrid reward architecture
 
Use Jupyter notebook guide in 5 minutes
Use Jupyter notebook guide in 5 minutesUse Jupyter notebook guide in 5 minutes
Use Jupyter notebook guide in 5 minutes
 
AlexNet and so on...
AlexNet and so on...AlexNet and so on...
AlexNet and so on...
 
Deep Learning AtoC with Image Perspective
Deep Learning AtoC with Image PerspectiveDeep Learning AtoC with Image Perspective
Deep Learning AtoC with Image Perspective
 
LOL win prediction
LOL win predictionLOL win prediction
LOL win prediction
 
How can we train with few data
How can we train with few dataHow can we train with few data
How can we train with few data
 
Domain adaptation gan
Domain adaptation ganDomain adaptation gan
Domain adaptation gan
 
Dense sparse-dense training for dnn and Other Models
Dense sparse-dense training for dnn and Other ModelsDense sparse-dense training for dnn and Other Models
Dense sparse-dense training for dnn and Other Models
 
Squeeeze models
Squeeeze modelsSqueeeze models
Squeeeze models
 

Kürzlich hochgeladen

Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...amitlee9823
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Valters Lauzums
 
Probability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter LessonsProbability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter LessonsJoseMangaJr1
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...ZurliaSoop
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% SecurePooja Nehwal
 
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men 🔝Thrissur🔝 Escor...
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men  🔝Thrissur🔝   Escor...➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men  🔝Thrissur🔝   Escor...
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men 🔝Thrissur🔝 Escor...amitlee9823
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...amitlee9823
 
Detecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning ApproachDetecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning ApproachBoston Institute of Analytics
 
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...karishmasinghjnh
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxolyaivanovalion
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysismanisha194592
 
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...SUHANI PANDEY
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...amitlee9823
 

Kürzlich hochgeladen (20)

Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
Probability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter LessonsProbability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter Lessons
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men 🔝Thrissur🔝 Escor...
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men  🔝Thrissur🔝   Escor...➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men  🔝Thrissur🔝   Escor...
➥🔝 7737669865 🔝▻ Thrissur Call-girls in Women Seeking Men 🔝Thrissur🔝 Escor...
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
 
Detecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning ApproachDetecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning Approach
 
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
 
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFx
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysis
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
 

All about that pooling

  • 2. (NOT) All about that Pooling in Image Processing
  • 4. What is Pooling/Subsampling for? Obj : Transform the "joint feature representation” into a new, more usable Const - discarding irrelevant detail => Invariance to changes in position/lighting, Robust to clutter, Compactness of representation... A Theoretical Analysis of Feature Pooling in Visual Recognition (2010) Pooling Operations
  • 5. This is the point Const - discarding irrelevant detail Pros Increasing Receptive Field Decrease Model Size Remove Noise Translation Invariance Cons Lose Details Lack (or NOT) of Equivariance Pooling Operations
  • 6. for TLDR; StaticLearnable Universal Particular Max Pooling Avg Pooling Fractional Pooling LP Pooling Wavelet Pooling Softmax Pooling Stochastic Pooling Blur Pooling Orderable Pooling Global Average Pooling Strided Convolution Mixed, Gated, Tree Pooling Local Importance Pooling Detail-Preserving Pooling Sensitive Insensitive Pooling Operations Global Feature Guided Local Pooling Spatial Pyramid Pooling
  • 7. for TLDR; Sensitive Insensitive Pooling Operations Response Sensitivity Someone, Orderable/Ranking/Attention Max Pooling Global Max Pooling Softmax Pooling Orderable Pooling Mixed, Gated, Tree Pooling Local Importance Pooling Detail-Preserving Pooling Spatial Pyramid Pooling Fractional Pooling Stochastic Pooling Strided Convolution Avg Pooling Wavelet Pooling LP Pooling Global Feature Guided Local Pooling Blur Pooling
  • 8. 시작하기 전 TMI CNN - Cat neuron response experiment (1962) Average Pooling - Lenet (1998) : Subsampling Max Pooling - Monkey neuron response exp (1999) -> DBN (2006) -> Hand gesture recognition with cnn (2010) Pooling Operations
  • 9. Main Pooling Papers Average Pooling Lenet’s Subsampling [2] Max Pooling Similar to Neuron’s (at least monkey) response than avg [1] LP Pooling Average Pool - Max Pool. With hyperparameter, we can get avg/weighted/max pooling Spatial Pyramid Pooling Overcome CNN’s fixed output (GAP), Diversiform Receptive Field Strided Convolution Trainable Pooling Pooling Operations
  • 10. Average Pooling vs Max Pooling Pooling Operations Feature Use all information with sum > Pros Backpropagation to all response > Cons Not robust to noise Feature Use highest value > Pros Robust to Noise > Cons Details are removed vs Suitable for Sparse Information - Image Classification Suitable for Dense Information - NLP [below 1] Avg / Response Insensitive Max / Response Sensitive Start with 90s
  • 11. Average Pooling / Max Pooling Balancing - Transformable 2012 Pooling Operations Convolutional Neural Networks Applied to House Numbers Digit Classification (2012) LP Pool by hyperparameter ‘p’, LP Pool is controllable from Avg(p=1) to Max(p=inf) - Exp on Lenet Base *SS: Single Stage, MS : Multi stage (Depth)
  • 12. Average Pooling / Max Pooling Balancing - Transformable 2017 Pooling Operations DCASE 2017 SUBMISSION: MULTIPLE INSTANCE LEARNING FOR SOUND EVENT DETECTION (2017) adaptive pooling operators for weakly labeled sound event detection (2018) Softmax Pool ( Auto Pool ) by hyperparameter ‘a’, controllable from Avg(a=0), Softmax(a=1) to Max(a=inf) * RAP : Restricted Auto Pool (add regularizer for moving near 0), CAP : Contrainted Auto Pool ( value const for moving near 0 ) * Strong - time-varying label / Weak - No time labeled - CNN based voice-spectrogram cls
  • 13. Average Pooling / Max Pooling Balancing - Hybrid 2015 Pooling Operations Generalizing Pooling Functions in Convolutional Neural Networks:Mixed, Gated, and Tree (2015) Mix/Gate Pool - Maybe Exp on (pool 2) Alexnet Base * Baseline : Max pool + Better Result & More Robust on transition ‘a’ parameter mix avg/max response
  • 14. Average Pooling / Max Pooling Balancing - Transformable + Hybrid 2019 Pooling Operations Global Feature Guided Local Pooling (2019) Global Feature Guided Local Pooling - Softmax Pooling인데, GAP-FC로 parameter 데이터 마다 조정! - More Depth, Pooling activated AVG/MAX *trainable `lambda` : 0, ‘rho’ :0 -> Avg `lambda` : inf, ‘rho’ :0 -> Max `lambda` : -inf, ‘rho’ :0 -> Min Response Position - Pooling Activation is Different by Cls (Imagenet)
  • 15. (Max Pooling) Only Response Sensitive! - Use Nth Max Responses 2016 - 2019 Pooling Operations Rank-based pooling for deep convolutional neural networks (2016) Ordinal Pooling (2019) Ordinal Pooling Weighting by Response Value Notable thing - At First Pooling, Closed to Avg. At Last, Close to Max * baseline :Modified Lenet Avg/GAP - MNIST
  • 16. Detail Please - Detail reinforce 2018 Pooling Operations Rapid, Detail-Preserving Image Downscaling (2016) Detail-Preserving Pooling in Deep Networks (2018)
  • 17. Detail Please - Detail reinforce 2018 Pooling Operations Rapid, Detail-Preserving Image Downscaling (2016) Detail-Preserving Pooling in Deep Networks (2018) (Assum) Original Image - Normed Downscaled Image == Details Detail Preserving Pooling *https://github.com/Tensor46/TensorMONK/ Blurring Image Detail Reflection * Trainable
  • 18. Detail Please - Detail reinforce 2019 Pooling Operations LIP: Local Importance-based Pooling (2019) Local Importance Pooling Calculate Pixel Importance (Gate) Reinforce Response by Gate LIP-AVG-Strided CAM - 코알라
  • 19. Hmm… Multiple Pooling - Diversity Bags Pooling Operations Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories (2006) Spatial Pyramid Pooling in Deep ConvolutionalNetworks for Visual Recognition (2014) Spatial Pyramid Pooling GAP
  • 20. Training, Training, Training - NONO Pooling! 2014 Pooling Operations Striving for simplicity, the all convolutional net (2014) Strided Convolution * BUT! FishNet reports Strided Conv is worse than Max Pool * Stride Convs can’t approximate MaxPool (Ordinal)
  • 21. Jackpot plz - Stochastic 2013 Pooling Operations Stochastic Pooling for Regularization of Deep Convolutional Neural Networks (2013) Stochastic Pooling - Train time : Stochastically Pool - Test time : Weight Pool
  • 22. Why only Integer division? - Rebellion of root 2015 Pooling Operations Fractional Max Pooling 2015 Fractional Max-Pooling - Random Kernel Size for Max pooling - for achieving root size downsample * In = 25, Out =18 (root 2) = 1.414 / 25/18 = 1.388
  • 23. Pooling has a WEAKNESS - Avoiding Kryptonium 2019 Pooling Operations Making Convolutional Networks Shift-Invariant Again 2019 https://richzhang.github.io/antialiased-cnns/ * Data Aug was removed Blur Pool
  • 24. Pooling has a WEAKNESS - Failed KING 2017 Pooling Operations CapsuleNet 2017 * Notable, “Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition (ICANN 2010) - Exp shows overlapping drops accuracy * By Contrast, “AlexNet (2012)” Report overlapping is helpful for prevent overfitting
  • 25. Family Tree Max Pooling Avg Pooling Spatial Pyramid Pool - 좀 더 다양하게 볼래 LP/Softmax Pool - 왔다 갔다할 수 있음! 족보 없음 Stochastic Pooling - 아무나 고를래! Wavelet Pooling - Edge는 무조건 중요! Ordinal Pool - Flex 여러개 봄 Mixed Pool - 동시에 둘다 볼래 Strided Convolution - 요즘은 러닝 시대 Rank Pool - 여러개 볼래 Blur Pool - Blurring하면 더 좋아짐! Fractional Pooling - 커널 크기 랜덤할래 Global Pool - 다 묻고 하나만 가! Detail Preserve Pool - Detail 어디감 Local Importance Pool - More Trainable Robust Attention Pool - GMP도 Trainable 하게 Global Feature Guided Local Pool - Input에 따라 avg/max 조절할래 ( Trainable LP )
  • 26.
  • 27. Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition (2010) - Overlapping pool drops accuracy A Theoretical Analysis of Feature Pooling in Visual Recognition (2010) - Proof if Response is sparse, max pooling is better than avg pooling Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNS (2018) Ask the locals: multi-way local pooling for image recognition (2011) Signal recovery from Pooling Representations (2014) stats385 Emergence of Invariance and Disentanglement in Deep Representations (2018) Quantifying Translation-Invariance in Convolutional Neural Networks (2017) A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction (2017) Learning to Linearize Under Uncertainty (2015) Pooling Analysis