Visual Attention Prediction (VAP) is a significant and imperative issue in the field of computer vision. Most of existing VAP methods are based on deep learning. However, they do not fully take advantage of the low-level contrast features while generating the visual attention map. In this paper, a novel VAP method is proposed to generate visual attention map via bio-inspired representation learning. The bio-inspired representation learning combines both low-level contrast and high-level semantic features simultaneously, which are developed by the fact that human eye is sensitive to the patches with high contrast and objects with high semantics. The proposed method is composed of three main steps: 1) feature extraction, 2) bio-inspired representation learning and 3) visual attention map generation. Firstly, the high-level semantic feature is extracted from the refined VGG16, while the low-level contrast feature is extracted by the proposed contrast feature extraction block in a deep network. Secondly, during bio-inspired representation learning, both the extracted low-level contrast and high-level semantic features are combined by the designed densely connected block, which is proposed to concatenate various features scale by scale. Finally, the weighted-fusion layer is exploited to generate the ultimate visual attention map based on the obtained representations after bio-inspired representation learning. Extensive experiments are performed to demonstrate the effectiveness of the proposed method.
Bio-inspired Color Constancy: From Gray Anchoring Theory to Gray Pixel Methods
MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China(教育部神经信息学重点实验室,生命科学与技术学院,电子科学与技术大学);School of Electronic Engineering and Automation, Guilin University of Electronic Technology(电子工程与自动化学院,桂林电子科技大学)
Bio-inspired AI: Integrating Biological Complexity into Artificial Intelligence
McGovern Institute for Brain Research, MIT(麻省理工学院麦戈文脑科学研究所);Allen Discovery Center at Tufts University(塔夫茨大学艾伦发现中心);Center for Brains, Minds, and Machines, MIT(麻省理工学院脑、心智与机器中心);Wyss Institute for Biologically Inspired Engineering, Harvard University(哈佛大学威斯生物启发工程研究所)
AIT Austrian Institute of Technology(奥地利理工学院);University of Zurich(苏黎世大学);ETH Zurich(苏黎世联邦理工学院);Western Sydney University(西悉尼大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
Learning audio and image representations with bio-inspired trainable feature extractors
Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen(格罗宁根大学约翰·伯努利数学与计算机科学研究所);University of Groningen(格罗宁根大学);University of Salerno(萨莱诺大学)