Memory-aided Contrastive Consensus Learning for Co-salient Object Detection

TL;DR

This paper introduces MCCL, a real-time, memory-augmented framework for co-salient object detection that improves accuracy and map quality through novel modules and adversarial learning, outperforming existing models.

Contribution

The paper proposes MCCL, a novel framework with group consensus aggregation, memory-based contrastive learning, and adversarial integrity strategies for improved co-salient object detection.

Findings

Achieves state-of-the-art performance on CoSOD benchmarks.

Operates at approximately 150 fps for real-time detection.

Outperforms 13 recent models with significant improvements in S-measure.

Abstract

Co-Salient Object Detection (CoSOD) aims at detecting common salient objects within a group of relevant source images. Most of the latest works employ the attention mechanism for finding common objects. To achieve accurate CoSOD results with high-quality maps and high efficiency, we propose a novel Memory-aided Contrastive Consensus Learning (MCCL) framework, which is capable of effectively detecting co-salient objects in real time (~150 fps). To learn better group consensus, we propose the Group Consensus Aggregation Module (GCAM) to abstract the common features of each image group; meanwhile, to make the consensus representation more discriminative, we introduce the Memory-based Contrastive Module (MCM), which saves and updates the consensus of images from different groups in a queue of memories. Finally, to improve the quality and integrity of the predicted maps, we develop an Adversarial Integrity Learning (AIL) strategy to make the segmented regions more likely composed of complete objects with less surrounding noise. Extensive experiments on all the latest CoSOD benchmarks demonstrate that our lite MCCL outperforms 13 cutting-edge models, achieving the new state of the art (~5.9% and ~6.2% improvement in S-measure on CoSOD3k and CoSal2015, respectively). Our source codes, saliency maps, and online demos are publicly available at https://github.com/ZhengPeng7/MCCL.