Fast saliency prediction based on multi-channels activation optimization
Affiliation:
1. Faculty of Information Science and Engineering, Ningbo University, Ningbo, China;2. School of Computer Science and Mathematics, Fujian University of Technology, Fuzhou 350118, China;1. Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, 200237, PR China;2. Department of Computer Science and Engineering, State Key Laboratory of Bioreactor Engineering, East China University of Science and Technology, Shanghai, 200237, PR China;3. Business Intelligence and Visualization Research Center, National Engineering Laboratory for Big Data Distribution and Exchange Technologies, Shanghai, 200436, PR China;4. Shanghai Engineering Research Center of Big Data & Internet Audience, Shanghai, 200072, PR China;5. Innovation College North-Chiang Mai University, 169 Moo3, Nong Kaew, Hang Dong, Chiang Mai 50230 Thailand;6. International College of Digital Innovation, Chiang Mai University, Chiang Mai, 50200, Thailand
Abstract:
The saliency prediction precision has improved rapidly with the development of deep learning technology, but the inference speed is slow due to the continuous deepening of networks. Hence, this paper proposes a fast saliency prediction model. Concretely, the siamese network backbone based on tailored EfficientNetV2 accelerates the inference speed while maintaining high performance. The shared parameters strategy further curbs parameter growth. Furthermore, we add multi-channel activation maps to optimize the fine features considering different channels and low-level visual features, which improves the interpretability of the model. Extensive experiments show that the proposed model achieves competitive performance on the standard benchmark datasets, and prove the effectiveness of our method in striking a balance between prediction accuracy and inference speed. Moreover, the small model size allows our method to be applied in edge devices. The code is available at: https://github.com/lscumt/fast-fixation-prediction.
