</> Code with Papers by Syntology

Datasets › DUTS

DUTS

Introduced by Lijun Wang et al. in Learning to Detect Salient Objects With Image-Level Supervision1 Jan 2017 archive 2025-07-28

DUTS is a saliency detection dataset containing 10,553 training images and 5,019 test images. All training images are collected from the ImageNet DET training/val sets, while test images are collected from the ImageNet DET test set and the SUN data set. Both the training and test set contain very challenging scenarios for saliency detection. Accurate pixel-level ground truths are manually annotated by 50 subjects.

Source: http://saliencydetection.net/duts/ Image Source: https://ieeexplore.ieee.org/document/8099887

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 5 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD, UHRSD) S-Measure 0.944 Bilateral Reference for High-Resolution Dichotomous... zhengpeng7/birefnet 31 Compare
Salient Object Detection DUTS-TE SAM2-UNet Smeasure 0.934 SAM2-UNet: Segment Anything 2 Makes Strong Encoder for... wzh0120/sam2-unet 8 Compare
Unsupervised Saliency Detection DUTS SelfMask maximal F-measure 88.2 Unsupervised Salient Object Detection with Spectral... noelshin/selfmask 3 Compare
Saliency Detection DUTS-test PFAN [zhao2019pyramid] (+) PRN MAE 0.0386 PatchRefineNet: Improving Binary Segmentation by... savinay95n/PatchRefineNet 2 Compare
Unsupervised Object Segmentation DUTS DeepCut mIoU 59.5 DeepCut: Unsupervised Segmentation using Graph Neural... sampl-weizmann/deepcut 1 Compare

Papers archive 2025-07-28

30 shown of 36 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 286. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement 0 1 11 Jan 2025 not harvested
FOCUS: Towards Universal Foreground Segmentation 1 1 9 Jan 2025 not harvested
SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation 1 1 16 Aug 2024 ran 5 of 9 samples (4 unverified)
Bilateral Reference for High-Resolution Dichotomous Image Segmentation 1 5 7 Jan 2024 ran 13 of 14 samples (1 unverified)
M³Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection 1 2 15 Sep 2023 not harvested
Explicit Visual Prompting for Universal Foreground Segmentations 2 1 29 May 2023 not harvested
DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering 1 1 12 Dec 2022 ran 4 of 8 samples (4 unverified)
PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization 1 1 12 Nov 2022 not harvested
MOVE: Unsupervised Movable Object Segmentation and Detection 1 1 14 Oct 2022 ran 3 of 6 samples (3 unverified; 6 pointer-only for licence)
Revisiting Image Pyramid Structure for High Resolution Salient Object Detection 3 1 20 Sep 2022 ran 3 of 11 samples (8 unverified)
A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels 3 1 7 Sep 2022 not harvested
SelfReformer: Self-Refined Network with Transformer for Salient Object Detection 1 2 23 May 2022 ran 1 of 2 samples (1 unverified)
Unsupervised Salient Object Detection with Spectral Cluster Voting 1 1 23 Mar 2022 ran 3 of 9 samples (6 unverified)
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut 1 1 23 Feb 2022 ran 1 of 1 samples (0 unverified)
TRACER: Extreme Attention Guided Salient Object Tracing Network 1 2 14 Dec 2021 ran 0 of 6 samples (6 unverified)
C⁴Net: Contextual Compression and Complementary Combination Network for Salient Object Detection 0 1 22 Oct 2021 not harvested
Saliency Detection via Global Context Enhanced Feature Fusion and Edge Weighted Loss 0 1 13 Oct 2021 not harvested
P2T: Pyramid Pooling Transformer for Scene Understanding 4 2 22 Jun 2021 not harvested
Recursive Contour Saliency Blending Network for Accurate Salient Object Detection 1 1 28 May 2021 not harvested
Uncertainty Inspired RGB-D Saliency Detection 4 2 7 Sep 2020 not harvested
Label Decoupling Framework for Salient Object Detection 1 1 25 Aug 2020 not harvested
F3Net: Fusion, Feedback and Focus for Salient Object Detection 4 1 26 Nov 2019 not harvested
BASNet: Boundary-Aware Salient Object Detection 3 1 1 Jun 2019 not harvested
A Simple Pooling-Based Design for Real-Time Salient Object Detection 5 1 21 Apr 2019 ran 1 of 3 samples (2 unverified)
Pyramid Feature Attention Network for Saliency detection 6 1 1 Mar 2019 ran 2 of 10 samples (8 unverified)
Progressive Attention Guided Recurrent Network for Salient Object Detection 1 1 1 Jun 2018 not harvested
Detect Globally, Refine Locally: A Novel Approach to Saliency Detection 0 1 1 Jun 2018 not harvested
A Stagewise Refinement Model for Detecting Salient Objects in Images 1 1 1 Oct 2017 not harvested
PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection 2 1 21 Aug 2017 not harvested
Learning Uncertain Convolutional Features for Accurate Saliency Detection 1 1 7 Aug 2017 not harvested

The full list of 36 is in the JSON twin.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

RGB Salient Object DetectionSaliency DetectionUnsupervised Object SegmentationSalient Object DetectionUnsupervised Saliency Detection

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • DUTS-test
  • DUTS-TE
  • DUTS

3 variant names, as the archive lists them.

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