Journal
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
Volume 31, Issue 3, Pages 877-889Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2020.2992054
Keywords
Feature extraction; Saliency detection; Task analysis; Convolution; Image segmentation; Semantics; Predictive models; Co-saliency detection; co-attention; FCN; deep supervised
Categories
Funding
- National Key Research and Development Program of China [2018YFB1701600]
- National Natural Science Foundation of China [U1804157, 41871283]
Ask authors/readers for more resources
This paper introduces a novel co-saliency detection framework CA-FCN, which incorporates a co-attention module to better identify common salient objects, improve detection performance, and achieve good results in experiments.
Co-saliency detection aims to detect common salient objects from a group of relevant images. Some attempts have been made with the Fully Convolutional Network (FCN) framework and achieve satisfactory detection results. However, due to stacking convolution layers and pooling operation, the boundary details tend to be lost. In addition, existing models often utilize the extracted features without discrimination, leading to redundancy in representation since actually not all features are helpful to the final prediction and some even bring distraction. In this paper, we propose a co-attention module embedded FCN framework, called as Co-Attention FCN (CA-FCN). Specifically, the co-attention module is plugged into the high-level convolution layers of FCN, which can assign larger attention weights on the common salient objects and smaller ones on the background and uncommon distractors to boost final detection performance. Extensive experiments on three popular co-saliency benchmark datasets demonstrate the superiority of the proposed CA-FCN, which outperforms state-of-the-arts in most cases. Besides, the effectiveness of our new co-attention module is also validated with ablation studies.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available