Bio-Inspired Representation Learning for Visual Attention Prediction
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 17 of its 61 references that are in the map. First posted on arXiv 9 Mar 2021.
Builds on
17 of 61 references.
References · 17
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2017Squeeze-and-Excitation Networkscited by 4,789
- 2016SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioningcited by 219
- 2014The Secrets of Salient Object Segmentationcited by 200
- 2016Deeply supervised salient object detection with short connectionscited by 196
- 2016Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Modelcited by 91
- 2014Convolutional Neural Networks at Constrained Time Costcited by 81
- 2017Deep Visual Attention Predictioncited by 70
- 2014Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNetcited by 60
- 2015DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixationscited by 48
5 more
- 2016Shallow and Deep Convolutional Networks for Saliency Predictioncited by 42
- 2017Co-saliency Detection for RGBD Images Based on Multi-constraint Feature Matching and Cross Label Propagationcited by 18
- 2017An Iterative Co-Saliency Framework for RGBD Imagescited by 14
- 2019Simultaneous Spectral-Spatial Feature Selection and Extraction for Hyperspectral Imagescited by 8
- 2017Embedding Visual Hierarchy with Deep Networks for Large-Scale Visual Recognitioncited by 4
Built on by
Citing papers per year: 2021: 2; 2022: 1.
3 papers.