Papers › CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement

CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement

11 Jan 2025arXiv:2501.06441archive 2025-07-28

Yijie Li, Hewei Wang, Aggelos Katsaggelos

Most of the current salient object detection approaches use deeper networks with large backbones to produce more accurate predictions, which results in a significant increase in computational complexity. A great number of network designs follow the pure UNet and Feature Pyramid Network (FPN) architecture which has limited feature extraction and aggregation ability which motivated us to design a lightweight post-decoder refinement module, the crossed post-decoder refinement (CPDR) to enhance the feature representation of a standard FPN or U-Net framework. Specifically, we introduce the Attention Down Sample Fusion (ADF), which employs channel attention mechanisms with attention maps generated by high-level representation to refine the low-level features, and Attention Up Sample Fusion (AUF), leveraging the low-level information to guide the high-level features through spatial attention. Additionally, we proposed the Dual Attention Cross Fusion (DACF) upon ADFs and AUFs, which reduces the number of parameters while maintaining the performance. Experiments on five benchmark datasets demonstrate that our method outperforms previous state-of-the-art approaches.

PaperPDF

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

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

DecoderObject DetectionRGB Salient Object DetectionSalient Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
RGB Salient Object Detection DUT-OMRON CPDR-L MAE 0.048 #15 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON CPDR-L mean E-Measure 0.883 #15 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON CPDR-L mean F-Measure 0.782 #15 of 18 Archive leaderboard report
RGB Salient Object Detection DUTS-TE CPDR-L MAE 0.034 #30 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE CPDR-L mean E-Measure 0.931 #30 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE CPDR-L mean F-Measure 0.853 #30 of 31 Archive leaderboard report
RGB Salient Object Detection ECSSD CPDR-L MAE 0.033 #12 of 14 Archive leaderboard report
RGB Salient Object Detection ECSSD CPDR-L mean E-Measure 0.951 #12 of 14 Archive leaderboard report
RGB Salient Object Detection ECSSD CPDR-L mean F-Measure 0.921 #12 of 14 Archive leaderboard report
RGB Salient Object Detection HKU-IS CPDR-L MAE 0.028 #12 of 14 Archive leaderboard report
RGB Salient Object Detection HKU-IS CPDR-L mean E-Measure 0.954 #12 of 14 Archive leaderboard report
RGB Salient Object Detection HKU-IS CPDR-L mean F-Measure 0.908 #12 of 14 Archive leaderboard report
RGB Salient Object Detection PASCAL-S CPDR-L MAE 0.061 #11 of 13 Archive leaderboard report
RGB Salient Object Detection PASCAL-S CPDR-L mean E-Measure 0.905 #11 of 13 Archive leaderboard report
RGB Salient Object Detection PASCAL-S CPDR-L mean F-Measure 0.836 #11 of 13 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 ConvolutionAttentionConcatenated Skip ConnectionConvolutionFPNMax PoolingReLUSoftmaxU-Net

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