GazeGAN: A Generative Adversarial Saliency Model based on Invariance
Analysis of Human Gaze During Scene Free Viewing
release_v6pm7g6r2bg7lgutkay4nlpiuu
by
Zhaohui Che and Ali Borji and Guangtao Zhai and Xiongkuo Min and
Guodong Guo and Patrick Le Callet
2019
Abstract
Data size is the bottleneck for developing deep saliency models, because
collecting eye-movement data is very time consuming and expensive. Most of
current studies on human attention and saliency modeling have used high quality
stereotype stimuli. In real world, however, captured images undergo various
types of transformations. Can we use these transformations to augment existing
saliency datasets? Here, we first create a novel saliency dataset including
fixations of 10 observers over 1900 images degraded by 19 types of
transformations. Second, by analyzing eye movements, we find that observers
look at different locations over transformed versus original images. Third, we
utilize the new data over transformed images, called data augmentation
transformation (DAT), to train deep saliency models. We find that label
preserving DATs with negligible impact on human gaze boost saliency prediction,
whereas some other DATs that severely impact human gaze degrade the
performance. These label preserving valid augmentation transformations provide
a solution to enlarge existing saliency datasets. Finally, we introduce a novel
saliency model based on generative adversarial network (dubbed GazeGAN). A
modified UNet is proposed as the generator of the GazeGAN, which combines
classic skip connections with a novel center-surround connection (CSC), in
order to leverage multi level features. We also propose a histogram loss based
on Alternative Chi Square Distance (ACS HistLoss) to refine the saliency map in
terms of luminance distribution. Extensive experiments and comparisons over 3
datasets indicate that GazeGAN achieves the best performance in terms of
popular saliency evaluation metrics, and is more robust to various
perturbations. Our code and data are available at:
https://github.com/CZHQuality/Sal-CFS-GAN.
In text/plain
format
Archived Files and Locations
application/pdf 7.1 MB
file_iouq4syvmrfabhiqx3bs7x67iy
|
arxiv.org (repository) web.archive.org (webarchive) |
1905.06803v1
access all versions, variants, and formats of this works (eg, pre-prints)