Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection

TL;DR

This paper introduces a novel co-salient object detection method that uses democratic prototype generation and self-contrastive learning to improve accuracy without extra information, outperforming previous methods.

Contribution

The paper proposes a democratic prototype generation and self-contrastive learning approach for more accurate co-salient object detection without additional data.

Findings

Achieves better performance than state-of-the-art methods on challenging datasets.

Improves MAE, F-measure, E-measure, and S-measure scores significantly.

Effective in real-world scenarios with complex backgrounds.

Abstract

Co-salient object detection, with the target of detecting co-existed salient objects among a group of images, is gaining popularity. Recent works use the attention mechanism or extra information to aggregate common co-salient features, leading to incomplete even incorrect responses for target objects. In this paper, we aim to mine comprehensive co-salient features with democracy and reduce background interference without introducing any extra information. To achieve this, we design a democratic prototype generation module to generate democratic response maps, covering sufficient co-salient regions and thereby involving more shared attributes of co-salient objects. Then a comprehensive prototype based on the response maps can be generated as a guide for final prediction. To suppress the noisy background information in the prototype, we propose a self-contrastive learning module, where both positive and negative pairs are formed without relying on additional classification information. Besides, we also design a democratic feature enhancement module to further strengthen the co-salient features by readjusting attention values. Extensive experiments show that our model obtains better performance than previous state-of-the-art methods, especially on challenging real-world cases (e.g., for CoCA, we obtain a gain of 2.0% for MAE, 5.4% for maximum F-measure, 2.3% for maximum E-measure, and 3.7% for S-measure) under the same settings. Code will be released soon.