</> Code with Papers by Syntology

Papers › Taking a Deeper Look at Co-Salient Object Detection

Taking a Deeper Look at Co-Salient Object Detection

1 Jun 2020CVPR 2020 6archive 2025-07-28

Deng-Ping Fan, Zheng Lin, Ge-Peng Ji, Dingwen Zhang, Huazhu Fu, Ming-Ming Cheng

Co-salient object detection (CoSOD) is a newly emerging and rapidly growing branch of salient object detection (SOD), which aims to detect the co-occurring salient objects in multiple images. However, existing CoSOD datasets often have a serious data bias, which assumes that each group of images contains salient objects of similar visual appearances. This bias results in the ideal settings and the effectiveness of the models, trained on existing datasets, may be impaired in real-life situations, where the similarity is usually semantic or conceptual. To tackle this issue, we first collect a new high-quality dataset, named CoSOD3k, which contains 3,316 images divided into 160 groups with multiple level annotations, i.e., category, bounding box, object, and instance levels. CoSOD3k makes a significant leap in terms of diversity, difficulty and scalability, benefiting related vision tasks. Besides, we comprehensively summarize 34 cutting-edge algorithms, benchmarking 19 of them over four existing CoSOD datasets (MSRC, iCoSeg, Image Pair and CoSal2015) and our CoSOD3k with a total of 61K images (largest scale), and reporting group-level performance analysis. Finally, we discuss the challenge and future work of CoSOD. Our study would give a strong boost to growth in the CoSOD community. Benchmark toolbox and results are available on our project page.

PaperPDFCode

Code

DengPingFan/CoEGNet pytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BenchmarkingCo-Salient Object DetectionObjectObject DetectionRGB Salient Object DetectionSalient Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Co-Salient Object Detection CoSOD3k CoEG-Net MAE 0.084 #8 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k CoEG-Net S-measure 0.778 #8 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k CoEG-Net max E-measure 0.837 #8 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k CoEG-Net max F-measure 0.758 #8 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k CoEG-Net mean E-measure 0.817 #8 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k CoEG-Net mean F-measure 0.748 #8 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 CoEG-Net MAE 0.077 #8 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 CoEG-Net S-measure 0.836 #8 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 CoEG-Net max E-measure 0.882 #8 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 CoEG-Net max F-measure 0.832 #8 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 CoEG-Net mean E-measure 0.867 #8 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 CoEG-Net mean F-measure 0.827 #8 of 10 Archive leaderboard report
Co-Salient Object Detection iCoSeg CoEG-Net MAE 0.060 #2 of 2 Archive leaderboard report
Co-Salient Object Detection iCoSeg CoEG-Net S-measure 0.875 #2 of 2 Archive leaderboard report
Co-Salient Object Detection iCoSeg CoEG-Net max E-measure 0.912 #2 of 2 Archive leaderboard report
Co-Salient Object Detection iCoSeg CoEG-Net max F-measure 0.876 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections