{"url":"/dataset/sun-seg-hard","name":"SUN-SEG-Hard (Unseen)","full_name":null,"description_markdown":"The SUN-SEG dataset is a high-quality per-frame annotated VPS dataset, which includes 158,690 frames from the famous SUN dataset. It extends the labels with diverse types, i.e., object mask, boundary, scribble, polygon, and visual attribute. It also introduces the pathological information from the original SUN dataset, including pathological classification labels, location information, and shape information.\r\n\r\nNotably, the origin SUN dataset has 113 colonoscopy videos, including 100 positive cases with 49, 136 polyp frames and 13 negative cases with 109, 554 non-polyp frames. It manually trims them into 378 positive and 728 negative short clips, meanwhile maintaining their intrinsic consecutive relationship. Such data pre-processing ensures each clip has around 3~11s duration at a real-time frame rate (i.e., 30 fps), which promotes the fault-tolerant margin for various algorithms and devices. To this end, the re-organized SUN-SEG contains 1, 106 short video clips with 158, 690 video frames totally, offering a solid foundation to build a representative benchmark.\r\n\r\nAs such, it yields the final version of our SUN-SEG dataset, which includes 49,136 polyp frames (i.e., positive part) and 109,554 non-polyp frames (i.e., negative part) taken from different 285 and 728 colonoscopy videos clips, as well as the corresponding annotations.","description_withheld":null,"homepage":"https://github.com/GewelsJI/VPS","introduced_date":"2022-07-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/video-polyp-segmentation-a-deep-learning","title":"Video Polyp Segmentation: A Deep Learning Perspective","first_author":"Ge-Peng Ji","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Medical","url":"/datasets/modality/medical"},{"name":"RGB Video","url":"/datasets/modality/rgb-video"}],"tasks":[{"name":"Video Polyp Segmentation","url":"/task/video-polyp-segmentation","datasets_with_task":"/datasets/task/video-polyp-segmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SUN-SEG-Hard (Unseen)"],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-polyp-segmentation-on-sun-seg-hard","task":"Video Polyp Segmentation","dataset_variant":"SUN-SEG-Hard (Unseen)","rows":18,"metrics":["Dice","S-Measure","mean E-measure","weighted F-measure","mean F-measure","Sensitivity","mean IoU"],"first_row_in_archive_order":{"model":"YOLO-SAM 2","paper":"/paper/self-prompting-polyp-segmentation-in","metrics":{"Dice":"0.902","S-Measure":"0.894","Sensitivity":"0.852","mean E-measure":"0.941","mean F-measure":"0.932"},"code_links":[{"title":"sajjad-sh33/yolo_sam2","url":"https://github.com/sajjad-sh33/yolo_sam2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/self-prompting-polyp-segmentation-in","title":"Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model","date":"2024-09-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/lgrnet-local-global-reciprocal-network-for","title":"LGRNet: Local-Global Reciprocal Network for Uterine Fibroid Segmentation in Ultrasound Videos","date":"2024-07-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sali-short-term-alignment-and-long-term-1","title":"SALI: Short-term Alignment and Long-term Interaction Network for Colonoscopy Video Polyp Segmentation","date":"2024-06-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/autosam-adapting-sam-to-medical-images-by","title":"AutoSAM: Adapting SAM to Medical Images by Overloading the Prompt Encoder","date":"2023-06-10","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/video-polyp-segmentation-a-deep-learning","title":"Video Polyp Segmentation: A Deep Learning Perspective","date":"2022-03-27","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-emergence-of-objectness-learning-zero","title":"The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos","date":"2021-11-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/full-duplex-strategy-for-video-object","title":"Full-Duplex Strategy for Video Object Segmentation","date":"2021-08-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":8,"samples_ran":7,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/shallow-attention-network-for-polyp","title":"Shallow Attention Network for Polyp Segmentation","date":"2021-08-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/progressively-normalized-self-attention","title":"Progressively Normalized Self-Attention Network for Video Polyp Segmentation","date":"2021-05-18","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/dynamic-context-sensitive-filtering-network","title":"Dynamic Context-Sensitive Filtering Network for Video Salient Object Detection","date":"2021-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/matnet-motion-attentive-transition-network","title":"MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object Segmentation","date":"2020-08-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pranet-parallel-reverse-attention-network-for","title":"PraNet: Parallel Reverse Attention Network for Polyp Segmentation","date":"2020-06-13","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":9,"samples_ran":8,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/see-more-know-more-unsupervised-video-object-1","title":"See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks","date":"2020-01-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unet-a-nested-u-net-architecture-for-medical","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","date":"2018-07-18","rows_on_this_dataset":1,"code_links":34,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":28,"samples_ran":6,"samples_unverified":22,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/u-net-convolutional-networks-for-biomedical","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","date":"2015-05-18","rows_on_this_dataset":1,"code_links":487,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":757,"samples_ran":518,"samples_unverified":239,"pointer_only_for_licence":426,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":5,"samples_harvested":810,"samples_ran":539,"samples_unverified":271,"pointer_only_for_licence":428,"papers_with_no_sample_that_ran":1,"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."}