6. 6
Control the number of output words using a
recurrent neural network
Jin et al., Annotation Order Matters: Recurrent Image Annotator
for Arbitrary Length Image Tagging, In Proc. ICPR, 2016.
7. Car types identification
Plant species identification
◦ ImageCLEF 2013 Plant
Identification Challenge (1st place)
Character recognition
◦ ICDAR Script identification
challenge (3rd place)
7
Acura RLMitsubishi
Lancer
Toyota Camry
Audi S4 Honda Accord Mercedes-Benz C-Class
8. Stochastically switch the cross-entropy loss(CCE)and the
mean absolute error loss(MAE)
8Hataya et al., LOL: LEARNING TO OPTIMIZE LOSS SWITCHING UNDER LABEL NOISE, 2018.
9. There exist some “easy” examples which can be correctly
classified at the beginning stage of learning
“Hard” data matters more
9
Kishida et al., EMPIRICAL STUDY OF EASY AND HARD EXAMPLES IN CNN TRAINING, ICONIP 2019.
10. Co-segmentation: extract common objects in multiple images
10
Chen et al., Semantic Aware Attention Based Deep
Object Co-segmentation, In Proc. ACCV, 2018.
11. Han et al., "Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using
Highly-Rough Annotation on MR Images", In Proc. of CIKM, 2019.
Han et al., "Combining Noise-to-Image and Image-to-Image GANs: Brain MR Image Augmentation for Tumor Detection",
IEEE Access, Vol.7, pp.156966-156977, 2019.
12. Erasing texts in general images
[WACV’20]
Erasing general objects
[Lazarski, 2018]
12
https://www.youtube.com/watch?v=JvTvyOeAGbU
13. Diversification of decoding [ACL’19]
Resource-efficient MT
◦ Compression of word vectors (99% off!) [ICLR’18]
◦ Rapid decoding [ACL’18, AAAI’20]
13
Input
Beam
Search
Proposed
Syntactic Diversity
16. 16
a woman is slicing
some vegetables
a cat is trying to
eat the food
a dog is swimming
in the pool
Input
(frame
sequence)
Output (word sequence)
“Translation”
from
video to text!
<BOS> a woman is cooking in the kitchen <EOS>
context vector
17. Multimodal Machine Translation
[CICLING’19]
◦ Improve translation with the help of vision
17
Phrase localization [LREC’20]
◦ Identify the image region for a given phrase
20. Monday: Group meeting (2~3h)
◦ Short progress report by all, discussion, study session
◦ Mainly organized by PhD students
Wednesday: Main meeting (2~3h)
◦ Progress report (3~4 students)
◦ Presentation practice, etc.
Others
◦ One-on-one meeting
◦ Project meeting
No other hours on duty
20
21. Workstation (2GPUs) for each student
Share machines
◦ 4GPUs x 4
◦ 8GPUs x 2
Cloud computers
◦ University cloud system
◦ ABCI
21