Papers › Cascaded Partial Decoder for Fast and Accurate Salient Object Detection

Cascaded Partial Decoder for Fast and Accurate Salient Object Detection

18 Apr 2019CVPR 2019 6arXiv:1904.08739archive 2025-07-28

Zhe Wu, Li Su, Qingming Huang

Existing state-of-the-art salient object detection networks rely on aggregating multi-level features of pre-trained convolutional neural networks (CNNs). Compared to high-level features, low-level features contribute less to performance but cost more computations because of their larger spatial resolutions. In this paper, we propose a novel Cascaded Partial Decoder (CPD) framework for fast and accurate salient object detection. On the one hand, the framework constructs partial decoder which discards larger resolution features of shallower layers for acceleration. On the other hand, we observe that integrating features of deeper layers obtain relatively precise saliency map. Therefore we directly utilize generated saliency map to refine the features of backbone network. This strategy efficiently suppresses distractors in the features and significantly improves their representation ability. Experiments conducted on five benchmark datasets exhibit that the proposed model not only achieves state-of-the-art performance but also runs much faster than existing models. Besides, the proposed framework is further applied to improve existing multi-level feature aggregation models and significantly improve their efficiency and accuracy.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

wuzhe71/CPD officialmentioned in paperpytorch 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

Camouflaged Object SegmentationDecoderObject DetectionRGB Salient Object DetectionSalient Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Camouflaged Object Segmentation COD CPD MAE 0.059 #9 of 12 Archive leaderboard report
Camouflaged Object Segmentation COD CPD S-Measure 0.747 #9 of 12 Archive leaderboard report
Camouflaged Object Segmentation COD CPD Weighted F-Measure 0.508 #9 of 12 Archive leaderboard report
Camouflaged Object Segmentation PCOD_1200 CPD S-Measure 0.855 #13 of 16 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON CPD-R (ResNet50) F-measure 0.747 #14 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON CPD-R (ResNet50) MAE 0.056 #14 of 18 Archive leaderboard report
RGB Salient Object Detection ECSSD CPD-R (ResNet50) F-measure 0.917 #10 of 14 Archive leaderboard report
RGB Salient Object Detection ECSSD CPD-R (ResNet50) MAE 0.037 #10 of 14 Archive leaderboard report
RGB Salient Object Detection HKU-IS CPD-R (ResNet50) F-measure 0.891 #10 of 14 Archive leaderboard report
RGB Salient Object Detection HKU-IS CPD-R (ResNet50) MAE 0.034 #10 of 14 Archive leaderboard report
RGB Salient Object Detection ISTD CPD Balanced Error Rate 6.76 #1 of 7 Archive leaderboard report
RGB Salient Object Detection PASCAL-S CPD-R (ResNet50) F-measure 0.824 #9 of 13 Archive leaderboard report
RGB Salient Object Detection PASCAL-S CPD-R (ResNet50) MAE 0.072 #9 of 13 Archive leaderboard report
RGB Salient Object Detection SBU / SBU-Refine CPD Balanced Error Rate 4.19 #1 of 7 Archive leaderboard report
RGB Salient Object Detection UCF CPD Balanced Error Rate 7.21 #1 of 7 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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