Consensus-Driven Coarse-to-Fine Consistency Learning for Co-Salient Object Detection
Open Access
- 16 November 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
Abstract
Co-salient object detection aims to identify common salient objects within related group images. The key challenge involves effectively capturing and utilizing the intrinsic consensus across group representations. Existing methods usually mine consensus from global high-level semantics and inject it into basic multi-level features, yet suffer from two key challenges: incomplete consensus exploration due to limited structural modeling under scale/position variations, and non-consensus noise introduced during consensus utilization. In this paper, we propose a novel consensus-driven coarse-to-fine consistency learning method named CCFC, which explores and exploits semantic consensus to achieve multi-level consistent salient features in a coarse-to-fine learning manner. Specifically, we first design a semantic consensus mining module that jointly interacts local structures and global semantics to capture semantic consensus. Then, under the guidance of such consensus, we develop a consensus-driven feature interaction module, which discovers fine-grained low-level and mid-level consistent salient features with cross-attention mechanism. Collaborating with these two modules, the proposed CCFC adaptively propagates semantic consensus across each level consistent features, preserving discriminative consistent salient cues while filtering out redundant noise, and thus predicts co-salient objects with complete contents and clear boundaries. Extensive experiments on three challenging benchmark datasets verify that CCFC achieves superior performance over state-of-the-art methods, with 0.797 \(S_{\alpha}\) and 0.065 MAE on the challenging CoCA dataset. Source code is available at: https://github.com/xiye2002/CCFC.
This publication has 17 references indexed in Scilit:
- Saliency and correlation learning for co-salient object detectionEngineering Applications of Artificial Intelligence, 2025
- Multidimension Attention Network for Full-Reference Light Field Image Quality AssessmentIEEE Transactions on Instrumentation and Measurement, 2025
- Edge and semantic collaboration framework with cross coordination attention for co-saliency detectionKnowledge-Based Systems, 2025
- Co-salient object detection with consensus mining and consistency cross-layer interactive decodingImage and Vision Computing, 2025
- Co-saliency detection with two-stage co-attention mining and individual calibrationEngineering Applications of Artificial Intelligence, 2023
- TCNet: Co-Salient Object Detection via Parallel Interaction of Transformers and CNNsIEEE Transactions on Circuits and Systems for Video Technology, 2022
- PVT v2: Improved baselines with pyramid vision transformerComputational Visual Media, 2022
- Efficient Video Object Co-Localization With Co-Saliency Activated TrackletsIEEE Transactions on Circuits and Systems for Video Technology, 2018
- Detection of Co-salient Objects by Looking Deep and WideInternational Journal of Computer Vision, 2016
- Cluster-Based Co-Saliency DetectionIEEE Transactions on Image Processing, 2013