{"url":"/task/zero-shot-semantic-segmentation","name":"Zero-Shot Semantic Segmentation","slug":"zero-shot-semantic-segmentation","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":60,"papers_with_code":29,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/zero-shot-semantic-segmentation-on-coco-stuff","slug":"zero-shot-semantic-segmentation-on-coco-stuff","dataset":"COCO-Stuff","dataset_url":"/dataset/coco-stuff","rows_in_archive":15,"metrics":["Transductive Setting hIoU","Inductive Setting hIoU"],"first_row_in_archive_order":{"model":"OTSeg+","paper_title":"OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation","paper_url":"/paper/otseg-multi-prompt-sinkhorn-attention-for","paper_date":"2024-03-21","arxiv_id":"2403.14183","code_links":[{"title":"cubeyoung/OTSeg","url":"https://github.com/cubeyoung/OTSeg"}],"syntology":{"n":10,"n_ran":9,"n_unverified":1,"n_pointer_only":10}}},{"leaderboard":"/sota/zero-shot-semantic-segmentation-on-mess","slug":"zero-shot-semantic-segmentation-on-mess","dataset":"MESS","dataset_url":null,"rows_in_archive":13,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"CAT-Seg-L","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/zero-shot-semantic-segmentation-on-pascal-voc","slug":"zero-shot-semantic-segmentation-on-pascal-voc","dataset":"PASCAL VOC","dataset_url":"/dataset/pascal-voc","rows_in_archive":13,"metrics":["Transductive Setting hIoU","Inductive Setting hIoU"],"first_row_in_archive_order":{"model":"OTSeg+","paper_title":"OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation","paper_url":"/paper/otseg-multi-prompt-sinkhorn-attention-for","paper_date":"2024-03-21","arxiv_id":"2403.14183","code_links":[{"title":"cubeyoung/OTSeg","url":"https://github.com/cubeyoung/OTSeg"}],"syntology":{"n":10,"n_ran":9,"n_unverified":1,"n_pointer_only":10}}},{"leaderboard":"/sota/zero-shot-semantic-segmentation-on-ade20k-847","slug":"zero-shot-semantic-segmentation-on-ade20k-847","dataset":"ADE20K-847","dataset_url":"/dataset/ade20k","rows_in_archive":1,"metrics":["unseen mIoU"],"first_row_in_archive_order":{"model":"MAFT","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/ade20k","name":"ADE20K","full_name":"","num_papers_in_archive":1213},{"url":"/dataset/coco-stuff","name":"COCO-Stuff","full_name":"Common Objects in COntext-stuff","num_papers_in_archive":338},{"url":"/dataset/pascal-voc","name":"PASCAL VOC","full_name":"PASCAL Visual Object Classes Challenge","num_papers_in_archive":198}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":29,"of":29,"tagged_in_all":60,"items":[{"url":"/paper/efficientnet-rethinking-model-scaling-for","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","date":"2019-05-28","arxiv_id":"1905.11946","repositories_listed":144,"syntology":{"n":302,"n_ran":171,"n_unverified":131,"n_pointer_only":112}},{"url":"/paper/flair-vlm-with-fine-grained-language-informed","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","date":"2024-12-04","arxiv_id":"2412.03561","repositories_listed":2,"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":20}},{"url":"/paper/2112-14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","date":"2021-12-29","arxiv_id":"2112.14757","repositories_listed":2,"syntology":null},{"url":"/paper/context-aware-feature-generation-for-zero","title":"Context-aware Feature Generation for Zero-shot Semantic Segmentation","date":"2020-08-16","arxiv_id":"2008.06893","repositories_listed":2,"syntology":null},{"url":"/paper/190600817","title":"Zero-Shot Semantic Segmentation","date":"2019-06-03","arxiv_id":"1906.00817","repositories_listed":2,"syntology":null},{"url":"/paper/3d-pointzshots-geometry-aware-3d-point-cloud","title":"3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap","date":"2025-04-16","arxiv_id":"2504.12442","repositories_listed":1,"syntology":null},{"url":"/paper/openobj-open-vocabulary-object-level-neural","title":"OpenObj: Open-Vocabulary Object-Level Neural Radiance Fields with Fine-Grained Understanding","date":"2024-06-12","arxiv_id":"2406.08009","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-image-segmentation-via-recursive","title":"DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut","date":"2024-06-05","arxiv_id":"2406.02842","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/cascade-clip-cascaded-vision-language","title":"Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation","date":"2024-06-02","arxiv_id":"2406.00670","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/otseg-multi-prompt-sinkhorn-attention-for","title":"OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation","date":"2024-03-21","arxiv_id":"2403.14183","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_unverified":1,"n_pointer_only":10}},{"url":"/paper/exploring-regional-clues-in-clip-for-zero","title":"Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-the-potential-of-pre-trained-vision","title":"Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/spectral-prompt-tuning-unveiling-unseen","title":"Spectral Prompt Tuning:Unveiling Unseen Classes for Zero-Shot Semantic Segmentation","date":"2023-12-20","arxiv_id":"2312.12754","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/sclip-rethinking-self-attention-for-dense","title":"SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference","date":"2023-12-04","arxiv_id":"2312.01597","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/an-easy-zero-shot-learning-combination","title":"An easy zero-shot learning combination: Texture Sensitive Semantic Segmentation IceHrNet and Advanced Style Transfer Learning Strategy","date":"2023-09-30","arxiv_id":"2310.00310","repositories_listed":1,"syntology":null},{"url":"/paper/clip-diy-clip-dense-inference-yields-open","title":"CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free","date":"2023-09-25","arxiv_id":"2309.14289","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}},{"url":"/paper/what-a-mess-multi-domain-evaluation-of-zero","title":"What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation","date":"2023-06-27","arxiv_id":"2306.15521","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/delving-into-shape-aware-zero-shot-semantic","title":"Delving into Shape-aware Zero-shot Semantic Segmentation","date":"2023-04-17","arxiv_id":"2304.08491","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-semantic-segmentation-with","title":"Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network","date":"2023-04-03","arxiv_id":"2304.01198","repositories_listed":1,"syntology":null},{"url":"/paper/zegot-zero-shot-segmentation-through-optimal","title":"ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts","date":"2023-01-28","arxiv_id":"2301.12171","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-point-cloud-segmentation-by-1","title":"Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/zegclip-towards-adapting-clip-for-zero-shot","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","date":"2022-12-07","arxiv_id":"2212.03588","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/understanding-and-mitigating-overfitting-in","title":"Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models","date":"2022-11-04","arxiv_id":"2211.02219","repositories_listed":1,"syntology":null},{"url":"/paper/decoupling-zero-shot-semantic-segmentation","title":"Decoupling Zero-Shot Semantic Segmentation","date":"2021-12-15","arxiv_id":"2112.07910","repositories_listed":1,"syntology":null},{"url":"/paper/denseclip-extract-free-dense-labels-from-clip","title":"Extract Free Dense Labels from CLIP","date":"2021-12-02","arxiv_id":"2112.01071","repositories_listed":1,"syntology":null},{"url":"/paper/a-closer-look-at-self-training-for-zero-label","title":"A Closer Look at Self-training for Zero-Label Semantic Segmentation","date":"2021-04-21","arxiv_id":"2104.11692","repositories_listed":1,"syntology":null},{"url":"/paper/from-pixel-to-patch-synthesize-context-aware","title":"From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation","date":"2020-09-25","arxiv_id":"2009.12232","repositories_listed":1,"syntology":null},{"url":"/paper/learning-unbiased-zero-shot-semantic","title":"Learning unbiased zero-shot semantic segmentation networks via transductive transfer","date":"2020-07-01","arxiv_id":"2007.00515","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-projection-network-for-zero-and-few","title":"Semantic Projection Network for Zero- and Few-Label Semantic Segmentation","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":10,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}