Year: 2020
Type: preprint
Abstract: In this paper, we show that existing recognition and localization deep architectures, that have not been exposed to eye tracking data or any saliency datasets, are capable of predicting the human visual saliency. We term this as implicit saliency in deep neural networks. We calculate this implicit saliency using expectancy-mismatch hypothesis in an unsupervised fashion. Our experiments show that extracting saliency in this fashion provides comparable performance when measured against the state-of-art supervised algorithms. Additionally, the robustness outperforms those algorithms when we add large noise to the input images. Also, we show that semantic features contribute more than low-level features for human visual saliency detection.
Source: arXiv (Cornell University)
Authors: Sun, Yutong, Prabhushankar, Mohit, AlRegib, Ghassan
Institution: Georgia Institute of Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3047423286