Co-Saliency Detection with Co-Attention Fully Convolutional Network

TL;DR

This paper introduces CA-FCN, a co-attention fully convolutional network that enhances co-saliency detection by focusing on common salient objects, reducing distraction, and improving accuracy over existing methods.

Contribution

The paper proposes a novel co-attention module integrated into FCN for better feature discrimination in co-saliency detection, outperforming state-of-the-art methods.

Findings

CA-FCN outperforms existing methods on benchmark datasets.

The co-attention module effectively emphasizes common salient objects.

Ablation studies confirm the module's contribution to performance improvement.

Abstract

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.