Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features

TL;DR: This work introduces SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples and shows how adversarial training allows reaching state-of-the-art performance across different metrics when combined with a widely-used loss function like BCE.

TL;DR: Through a combination of knowledge distillation and Fisher pruning, this paper obtains much more runtime-efficient architectures for saliency prediction, achieving a 10x speedup for the same AUC performance as a state of the art network on the CAT2000 dataset.

TL;DR: A large number of image and video saliency models are reviewed and compared over two image benchmarks and two large scale video datasets and factors that contribute to the gap between models and humans are identified.

TL;DR: This work proposes a local-global fusion model for fixation prediction on an RGB-D image that combines global and local information through a content-aware fusion module (CAFM) structure.

TL;DR: To improve localization quality of the proposals while maintaining efficiency, a novel fast segmentation method is proposed and demonstrated its effectiveness for improving BING’s localization performance, when used in multi-thresholding straddling expansion (MTSE) post-processing.

TL;DR: A benchmark data set containing 300 natural images with eye tracking data from 39 observers is proposed to compare model performances and it is shown that human performance increases with the number of humans to a limit.

TL;DR: It is shown that a large fraction of the parameters (the weights of neural networks) are of less importance and do not need to be measured with high accuracy and therefore the reported experiments seem to be more realistic from a classical point of view.

TL;DR: A novel Boolean Map based Saliency model, based on a Gestalt principle of figure-ground segregation, that consistently achieves state-of-the-art performance compared with ten leading methods on five eye tracking datasets.