Papers › Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale...

Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing

1 Jun 2019CVPR 2019 6archive 2025-07-28

Kaihua Zhang, Tengpeng Li, Bo Liu, Qingshan Liu

In image co-saliency detection problem, one critical issue is how to model the concurrent pattern of the co-salient parts, which appears both within each image and across all the relevant images. In this paper, we propose a hierarchical image co-saliency detection framework as a coarse to fine strategy to capture this pattern. We first propose a mask-guided fully convolutional network structure to generate the initial co-saliency detection result. The mask is used for background removal and it is learned from the high-level feature response maps of the pre-trained VGG-net output. We next propose a multi-scale label smoothing model to further refine the detection result. The proposed model jointly optimizes the label smoothness of pixels and superpixels. Experiment results on three popular image co-saliency detection benchmark datasets including iCoseg, MSRC and Cosal2015 demonstrate the remarkable performance compared with the state-of-the-art methods.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Co-Salient Object DetectionSaliency DetectionSuperpixels

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Co-Salient Object Detection CoCA CSMG Mean F-measure 0.390 #9 of 10 Archive leaderboard report
Co-Salient Object Detection CoCA CSMG S-measure 0.627 #9 of 10 Archive leaderboard report
Co-Salient Object Detection CoCA CSMG max F-measure 0.499 #9 of 10 Archive leaderboard report
Co-Salient Object Detection CoCA CSMG mean E-measure 0.606 #9 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k CSMG MAE 0.157 #9 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k CSMG S-measure 0.711 #9 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k CSMG max E-measure 0.804 #9 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k CSMG max F-measure 0.709 #9 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 CSMG MAE 0.130 #10 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 CSMG S-measure 0.774 #10 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 CSMG max E-measure 0.842 #10 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 CSMG max F-measure 0.784 #10 of 10 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.

Methods

Label Smoothing

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