{"url":"/dataset/duts","name":"DUTS","full_name":null,"description_markdown":"**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.\r\n\r\nSource: [http://saliencydetection.net/duts/](http://saliencydetection.net/duts/)\r\nImage Source: [https://ieeexplore.ieee.org/document/8099887](https://ieeexplore.ieee.org/document/8099887)","description_withheld":null,"homepage":"http://saliencydetection.net/duts/","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-to-detect-salient-objects-with-image","title":"Learning to Detect Salient Objects With Image-Level Supervision","first_author":"Lijun Wang","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"RGB Salient Object Detection","url":"/task/salient-object-detection","datasets_with_task":"/datasets/task/salient-object-detection"},{"name":"Saliency Detection","url":"/task/saliency-detection","datasets_with_task":"/datasets/task/saliency-detection"},{"name":"Unsupervised Object Segmentation","url":"/task/unsupervised-object-segmentation","datasets_with_task":"/datasets/task/unsupervised-object-segmentation"},{"name":"Salient Object Detection","url":"/task/salient-object-detection-1","datasets_with_task":"/datasets/task/salient-object-detection-1"},{"name":"Unsupervised Saliency Detection","url":"/task/unsupervised-saliency-detection","datasets_with_task":"/datasets/task/unsupervised-saliency-detection"}],"languages":[],"variants":["DUTS-test","DUTS-TE","DUTS"],"data_loaders":[],"num_papers_in_archive":286,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/salient-object-detection-on-duts-te","task":"RGB Salient Object Detection","dataset_variant":"DUTS-TE","rows":31,"metrics":["S-Measure","max F-measure","mean E-Measure","MAE","mean F-Measure","Weighted F-Measure"],"first_row_in_archive_order":{"model":"BiRefNet (DUTS, HRSOD, UHRSD)","paper":"/paper/bilateral-reference-for-high-resolution","metrics":{"MAE":"0.018","S-Measure":"0.944","Weighted F-Measure":"0.920","max F-measure":"0.943","mean E-Measure":"0.962","mean F-Measure":"0.925"},"code_links":[{"title":"zhengpeng7/birefnet","url":"https://github.com/zhengpeng7/birefnet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/salient-object-detection-on-duts-te-1","task":"Salient Object Detection","dataset_variant":"DUTS-TE","rows":8,"metrics":["Smeasure","E-measure","MAE","max_F1"],"first_row_in_archive_order":{"model":"SAM2-UNet","paper":"/paper/sam2-unet-segment-anything-2-makes-strong","metrics":{"E-measure":" 0.959","MAE":"0.020","Smeasure":"0.934"},"code_links":[{"title":"wzh0120/sam2-unet","url":"https://github.com/wzh0120/sam2-unet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-saliency-detection-on-duts","task":"Unsupervised Saliency Detection","dataset_variant":"DUTS","rows":3,"metrics":["maximal F-measure","Accuracy","IoU"],"first_row_in_archive_order":{"model":"SelfMask","paper":"/paper/unsupervised-salient-object-detection-with","metrics":{"Accuracy":"93.3","IoU":"66","maximal F-measure":"88.2"},"code_links":[{"title":"noelshin/selfmask","url":"https://github.com/noelshin/selfmask"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/saliency-detection-on-duts-test","task":"Saliency Detection","dataset_variant":"DUTS-test","rows":2,"metrics":["MAE"],"first_row_in_archive_order":{"model":"PFAN [zhao2019pyramid] (+) PRN","paper":"/paper/threshnet-segmentation-refinement-inspired-by","metrics":{"MAE":"0.0386"},"code_links":[{"title":"savinay95n/PatchRefineNet","url":"https://github.com/savinay95n/PatchRefineNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-object-segmentation-on-duts","task":"Unsupervised Object Segmentation","dataset_variant":"DUTS","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"DeepCut","paper":"/paper/deepcut-unsupervised-segmentation-using-graph","metrics":{"mIoU":"59.5"},"code_links":[{"title":"sampl-weizmann/deepcut","url":"https://github.com/sampl-weizmann/deepcut"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/cpdr-towards-highly-efficient-salient-object","title":"CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement","date":"2025-01-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/focus-towards-universal-foreground","title":"FOCUS: Towards Universal Foreground Segmentation","date":"2025-01-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sam2-unet-segment-anything-2-makes-strong","title":"SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation","date":"2024-08-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":5,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bilateral-reference-for-high-resolution","title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","date":"2024-01-07","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":13,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/m-3-net-multilevel-mixed-and-multistage","title":"M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection","date":"2023-09-15","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/explicit-visual-prompting-for-universal","title":"Explicit Visual Prompting for Universal Foreground Segmentations","date":"2023-05-29","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deepcut-unsupervised-segmentation-using-graph","title":"DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering","date":"2022-12-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":4,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/threshnet-segmentation-refinement-inspired-by","title":"PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization","date":"2022-11-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/move-unsupervised-movable-object-segmentation","title":"MOVE: Unsupervised Movable Object Segmentation and Detection","date":"2022-10-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":3,"samples_unverified":3,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/revisiting-image-pyramid-structure-for-high","title":"Revisiting Image Pyramid Structure for High Resolution Salient Object Detection","date":"2022-09-20","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":3,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-weakly-supervised-learning-framework-for","title":"A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels","date":"2022-09-07","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/selfreformer-self-refined-network-with","title":"SelfReformer: Self-Refined Network with Transformer for Salient Object Detection","date":"2022-05-23","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unsupervised-salient-object-detection-with","title":"Unsupervised Salient Object Detection with Spectral Cluster Voting","date":"2022-03-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":3,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-supervised-transformers-for-unsupervised","title":"Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut","date":"2022-02-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tracer-extreme-attention-guided-salient","title":"TRACER: Extreme Attention Guided Salient Object Tracing Network","date":"2021-12-14","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/c-4-net-contextual-compression-and","title":"C$^{4}$Net: Contextual Compression and Complementary Combination Network for Salient Object Detection","date":"2021-10-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/saliency-detection-via-global-context","title":"Saliency Detection via Global Context Enhanced Feature Fusion and Edge Weighted Loss","date":"2021-10-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/p2t-pyramid-pooling-transformer-for-scene","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","date":"2021-06-22","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/recursive-contour-saliency-blending-network","title":"Recursive Contour Saliency Blending Network for Accurate Salient Object Detection","date":"2021-05-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/uncertainty-inspired-rgb-d-saliency-detection","title":"Uncertainty Inspired RGB-D Saliency Detection","date":"2020-09-07","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/label-decoupling-framework-for-salient-object-1","title":"Label Decoupling Framework for Salient Object Detection","date":"2020-08-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/f3net-fusion-feedback-and-focus-for-salient","title":"F3Net: Fusion, Feedback and Focus for Salient Object Detection","date":"2019-11-26","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/basnet-boundary-aware-salient-object","title":"BASNet: Boundary-Aware Salient Object Detection","date":"2019-06-01","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/a-simple-pooling-based-design-for-real-time","title":"A Simple Pooling-Based Design for Real-Time Salient Object Detection","date":"2019-04-21","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pyramid-feature-selective-network-for","title":"Pyramid Feature Attention Network for Saliency detection","date":"2019-03-01","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":2,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/progressive-attention-guided-recurrent","title":"Progressive Attention Guided Recurrent Network for Salient Object Detection","date":"2018-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/detect-globally-refine-locally-a-novel","title":"Detect Globally, Refine Locally: A Novel Approach to Saliency Detection","date":"2018-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-stagewise-refinement-model-for-detecting","title":"A Stagewise Refinement Model for Detecting Salient Objects in Images","date":"2017-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/picanet-learning-pixel-wise-contextual","title":"PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection","date":"2017-08-21","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/learning-uncertain-convolutional-features-for","title":"Learning Uncertain Convolutional Features for Accurate Saliency Detection","date":"2017-08-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/amulet-aggregating-multi-level-convolutional","title":"Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection","date":"2017-08-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/non-local-deep-features-for-salient-object","title":"Non-Local Deep Features for Salient Object Detection","date":"2017-07-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/instance-level-salient-object-segmentation","title":"Instance-Level Salient Object Segmentation","date":"2017-04-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deeply-supervised-salient-object-detection","title":"Deeply supervised salient object detection with short connections","date":"2016-11-15","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dhsnet-deep-hierarchical-saliency-network-for","title":"DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection","date":"2016-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-contrast-learning-for-salient-object","title":"Deep Contrast Learning for Salient Object Detection","date":"2016-03-07","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":12,"samples_harvested":82,"samples_ran":36,"samples_unverified":46,"pointer_only_for_licence":6,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}