# A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection

arXiv: https://arxiv.org/abs/2208.06615 · HTML: https://mlsanity.com/paper/2208.06615/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 13 Aug 2022.

## Builds on (most cited first, 8 of 8)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Re-thinking Co-Salient Object Detection](https://mlsanity.com/paper/2007.03380/) (2020)
- [Gradient-Induced Co-Saliency Detection](https://mlsanity.com/paper/2004.13364/) (2020)
- [Group Collaborative Learning for Co-Salient Object Detection](https://mlsanity.com/paper/2104.01108/) (2021)
- [Learning Dual Semantic Relations with Graph Attention for Image-Text Matching](https://mlsanity.com/paper/2010.11550/) (2020)
- [CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection](https://mlsanity.com/paper/2011.04887/) (2020)
- [HSCS: Hierarchical Sparsity Based Co-saliency Detection for RGBD Images](https://mlsanity.com/paper/1811.06679/) (2018)

## Built on by (most cited first, 1 of 1)

- [Vision-Language Matching for Text-to-Image Synthesis via Generative Adversarial Networks](https://mlsanity.com/paper/2208.09596/) (2022)

## Abstract (arXiv)

Co-saliency detection (CoSOD) aims at discovering the repetitive salient objects from multiple images. Two primary challenges are group semantics extraction and noise object suppression. In this paper, we present a unified Two-stage grOup semantics PropagatIon and Contrastive learning NETwork (TopicNet) for CoSOD. TopicNet can be decomposed into two substructures, including a two-stage group semantics propagation module (TGSP) to address the first challenge and a contrastive learning module (CLM) to address the second challenge. Concretely, for TGSP, we design an image-to-group propagation module (IGP) to capture the consensus representation of intra-group similar features and a group-to-pixel propagation module (GPP) to build the relevancy of consensus representation. For CLM, with the design of positive samples, the semantic consistency is enhanced. With the design of negative samples, the noise objects are suppressed. Experimental results on three prevailing benchmarks reveal that TopicNet outperforms other competitors in terms of various evaluation metrics.