</> Code with Papers by Syntology

Datasets › DIS5K

DIS5K (Dichotomous Image Segmentation (DIS) Dataset)

Introduced by Xuebin Qin et al. in Highly Accurate Dichotomous Image Segmentation6 Mar 2022 archive 2025-07-28

To build the highly accurate Dichotomous Image Segmentation dataset (DIS5K), we first manually collected over 12,000 images from Flickr1 based on our pre-designed keywords. Then, we obtained 5,470 images of 22 groups and 225 categories from the 12,000 images according to the structural complexities of the objects. Each image is then manually labeled with pixel-wise accuracy using GIMP. The labeled targets in DIS5K mainly focus on the “objects of the images defined by the pre-designed keywords (categories)” regardless of their characteristics e.g., salient, common, camouflaged, meticulous, etc. The average per-image labeling time is ∼30 minutes and some images cost up to 10 hours.

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
Dichotomous Image Segmentation DIS-VD BEN_Base max F-Measure 0.923 BEN: Using Confidence-Guided Matting for Dichotomous... PramaLLC/BEN 24 Compare
Dichotomous Image Segmentation DIS-TE1 PDFNet max F-Measure 0.890 Patch-Depth Fusion: Dichotomous Image Segmentation via... tennine2077/pdfnet 22 Compare
Dichotomous Image Segmentation DIS-TE2 PDFNet max F-Measure 0.921 Patch-Depth Fusion: Dichotomous Image Segmentation via... tennine2077/pdfnet 22 Compare
Dichotomous Image Segmentation DIS-TE3 PDFNet max F-Measure 0.936 Patch-Depth Fusion: Dichotomous Image Segmentation via... tennine2077/pdfnet 22 Compare
Dichotomous Image Segmentation DIS-TE4 MVANet max F-Measure 0.912 Multi-view Aggregation Network for Dichotomous Image Segmentation qianyu-dlut/mvanet 22 Compare

Papers archive 2025-07-28

22 shown of 22 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 39. 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
Patch-Depth Fusion: Dichotomous Image Segmentation via Fine-Grained Patch Strategy and Depth Integrity-Prior 1 5 8 Mar 2025 not harvested
BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation 1 2 8 Jan 2025 not harvested
Multi-view Aggregation Network for Dichotomous Image Segmentation 1 5 11 Apr 2024 ran 8 of 9 samples (1 unverified)
Bilateral Reference for High-Resolution Dichotomous Image Segmentation 1 5 7 Jan 2024 ran 13 of 14 samples (1 unverified)
Revisiting Image Pyramid Structure for High Resolution Salient Object Detection 3 10 20 Sep 2022 ran 3 of 11 samples (8 unverified)
Highly Accurate Dichotomous Image Segmentation 1 5 6 Mar 2022 ran 9 of 10 samples (1 unverified)
Rethinking BiSeNet For Real-time Semantic Segmentation 6 5 27 Apr 2021 ran 8 of 16 samples (8 unverified)
Camouflaged Object Segmentation with Distraction Mining 1 5 21 Apr 2021 ran 4 of 9 samples (5 unverified; 9 pointer-only for licence)
Concealed Object Detection 1 5 20 Feb 2021 ran 3 of 3 samples (0 unverified)
HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation 1 5 21 Dec 2020 not harvested
Suppress and Balance: A Simple Gated Network for Salient Object Detection 3 5 16 Jul 2020 not harvested
U²-Net: Going Deeper with Nested U-Structure for Salient Object Detection 29 5 18 May 2020 ran 4 of 42 samples (38 unverified; 2 pointer-only for licence)
Global Context-Aware Progressive Aggregation Network for Salient Object Detection 2 5 2 Mar 2020 ran 5 of 13 samples (8 unverified; 13 pointer-only for licence)
F3Net: Fusion, Feedback and Focus for Salient Object Detection 4 5 26 Nov 2019 not harvested
Deep High-Resolution Representation Learning for Visual Recognition 42 5 20 Aug 2019 ran 3 of 34 samples (31 unverified; 16 pointer-only for licence)
BASNet: Boundary-Aware Salient Object Detection 3 5 1 Jun 2019 not harvested
Searching for MobileNetV3 67 5 6 May 2019 ran 58 of 105 samples (47 unverified; 46 pointer-only for licence)
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation 21 5 2 Aug 2018 ran 6 of 18 samples (12 unverified; 1 pointer-only for licence)
Rethinking Atrous Convolution for Semantic Image Segmentation 77 5 17 Jun 2017 ran 3 of 7 samples (4 unverified; 3 pointer-only for licence)
ICNet for Real-Time Semantic Segmentation on High-Resolution Images 18 5 27 Apr 2017 not harvested
Pyramid Scene Parsing Network 67 5 4 Dec 2016 ran 7 of 29 samples (22 unverified; 5 pointer-only for licence)
U-Net: Convolutional Networks for Biomedical Image Segmentation 487 5 18 May 2015 ran 510 of 757 samples (247 unverified; 426 pointer-only for licence)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Dichotomous Image Segmentation

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • DIS5K
  • DIS-VD
  • DIS-TE1
  • DIS-TE2
  • DIS-TE3
  • DIS-TE4

6 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