Slides by Junting Pan at the UPC Computer Vision Reading Group about the paper:
M Cornia, L Baraldi, G Serra, R Cucchiara. Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model. arXiv preprint arXiv:1611.09571
Statistics notes ,it includes mean to index numbers
Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model (UPC Reading Group 2017)
1. Predicting Human Eye Fixations via an LSTM-based
Saliency Attentive Model
Junting Pan
M Cornia, L Baraldi, G Serra, R Cucchiara. Predicting Human Eye Fixations via an LSTM-based Saliency
Attentive Model. arXiv preprint arXiv:1611.09571
19. 4. Implementation Details
- Batch size : 10
- RMSprop optimizer
- Residual Network are initialized using ResNet-50 pre trained on ImageNet
- Loss Function : KL-Divergence
- Learning rate : 10e-4, decay by a factor of 10 every two epochs
26. 6. Conclusions
- New Saliency Attentive Model for fixation prediction.
- Attentive Convolutional LSTM that is specifically designed to sequentially
focus on the most salient regions of input images.
- Residual Architecture with dilated filters that maintains the spatial resolution.