{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/batch-dice-loss","entry":"batch_dice_loss","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","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)"},"n_papers":60,"n_papers_ran":7,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":8,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":60,"n_places_pointer_only":14,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":4},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2508.08612","paper":"/paper/arxiv-2508-08612","title":"Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"JiahuaDong/HVPL","path":"hvpl/modeling/vita_matcher.py","file_url":"https://github.com/JiahuaDong/HVPL/blob/HEAD/hvpl/modeling/vita_matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2507.12857","paper":"/paper/score-scene-context-matters-in-open","title":"SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation","date":"2025-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HuangShiqi128/SCORE","path":"score/modeling/matcher.py","file_url":"https://github.com/HuangShiqi128/SCORE/blob/HEAD/score/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2507.08555","paper":"/paper/disentangling-instance-and-scene-contexts-for","title":"Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion","date":"2025-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Enyu-Liu/DISC","path":"maskdino/models/matcher.py","file_url":"https://github.com/Enyu-Liu/DISC/blob/HEAD/maskdino/models/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2506.22624","paper":"/paper/seg-r1-segmentation-can-be-surprisingly","title":"Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning","date":"2025-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"geshang777/FOCUS","path":"focus/modeling/matcher.py","file_url":"https://github.com/geshang777/FOCUS/blob/HEAD/focus/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2506.02493","paper":"/paper/towards-in-the-wild-3d-plane-reconstruction-1","title":"Towards In-the-wild 3D Plane Reconstruction from a Single Image","date":"2025-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jcliu0428/ZeroPlane","path":"ZeroPlane/modeling/matcher.py","file_url":"https://github.com/jcliu0428/ZeroPlane/blob/HEAD/ZeroPlane/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2412.03069","paper":"/paper/tokenflow-unified-image-tokenizer-for","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","date":"2024-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruohaoguo/avis","path":"avism/modeling/avism_matcher.py","file_url":"https://github.com/ruohaoguo/avis/blob/HEAD/avism/modeling/avism_matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2412.02402","paper":"/paper/rg-san-rule-guided-spatial-awareness-network","title":"RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation","date":"2024-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sosppxo/RG-SAN","path":"rg_san/model/loss.py","file_url":"https://github.com/sosppxo/RG-SAN/blob/HEAD/rg_san/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"89f8d423e0baf041","mcp_get_code":{"code_sha256":"89f8d423e0baf041"}},{"arxiv_id":"2410.04842","paper":"/paper/a-simple-image-segmentation-framework-via-in","title":"A Simple Image Segmentation Framework via In-Context Examples","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aim-uofa/SINE","path":"sine/model/matcher.py","file_url":"https://github.com/aim-uofa/SINE/blob/HEAD/sine/model/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2408.01044","paper":"/paper/2408-01044","title":"Boosting Gaze Object Prediction via Pixel-level Supervision from Vision Foundation Model","date":"2024-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinyang06/SamGOP","path":"maskGOP/modeling/detr_matcher.py","file_url":"https://github.com/jinyang06/SamGOP/blob/HEAD/maskGOP/modeling/detr_matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2407.20664","paper":"/paper/3d-gres-generalized-3d-referring-expression","title":"3D-GRES: Generalized 3D Referring Expression Segmentation","date":"2024-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sosppxo/MDIN","path":"gres_model/model/loss.py","file_url":"https://github.com/sosppxo/MDIN/blob/HEAD/gres_model/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"89f8d423e0baf041","mcp_get_code":{"code_sha256":"89f8d423e0baf041"}},{"arxiv_id":"2407.16696","paper":"/paper/partglee-a-foundation-model-for-recognizing","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ProvenceStar/PartGLEE","path":"projects/PartGLEE/partglee/models/matcher.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/models/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2407.10084","paper":"/paper/part2object-hierarchical-unsupervised-3d","title":"Part2Object: Hierarchical Unsupervised 3D Instance Segmentation","date":"2024-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chengshiest/part2object","path":"models/matcher.py","file_url":"https://github.com/chengshiest/part2object/blob/HEAD/models/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2407.03263","paper":"/paper/a-unified-framework-for-3d-scene","title":"A Unified Framework for 3D Scene Understanding","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dk-liang/uniseg3d","path":"uniseg3d/instance_criterion.py","file_url":"https://github.com/dk-liang/uniseg3d/blob/HEAD/uniseg3d/instance_criterion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"466d41757b35f3b7","mcp_get_code":{"code_sha256":"466d41757b35f3b7"}},{"arxiv_id":"2406.09829","paper":"/paper/open-vocabulary-semantic-segmentation-with-4","title":"Open-Vocabulary Semantic Segmentation with Image Embedding Balancing","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"slonetime/EBSeg","path":"ebseg/model/matcher.py","file_url":"https://github.com/slonetime/EBSeg/blob/HEAD/ebseg/model/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2405.10370","paper":"/paper/grounded-3d-llm-with-referent-tokens","title":"Grounded 3D-LLM with Referent Tokens","date":"2024-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenRobotLab/Grounded_3D-LLM","path":"models/matcher.py","file_url":"https://github.com/OpenRobotLab/Grounded_3D-LLM/blob/HEAD/models/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2404.14657","paper":"/paper/progressive-token-length-scaling-in","title":"Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation","date":"2024-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abhishekaich27/proscale-pytorch","path":"mask2former/modeling/matcher.py","file_url":"https://github.com/abhishekaich27/proscale-pytorch/blob/HEAD/mask2former/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2404.03645","paper":"/paper/decoupling-static-and-hierarchical-motion","title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heshuting555/DsHmp","path":"dshmp/modeling/vita_matcher.py","file_url":"https://github.com/heshuting555/DsHmp/blob/HEAD/dshmp/modeling/vita_matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2402.19422","paper":"/paper/pem-prototype-based-efficient-maskformer-for","title":"PEM: Prototype-based Efficient MaskFormer for Image Segmentation","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"niccolocavagnero/pem","path":"pem/modeling/matcher.py","file_url":"https://github.com/niccolocavagnero/pem/blob/HEAD/pem/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2402.18115","paper":"/paper/univs-unified-and-universal-video","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minghanli/univs","path":"univs/modeling/video_matcher.py","file_url":"https://github.com/minghanli/univs/blob/HEAD/univs/modeling/video_matcher.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a03c334f626ed752","mcp_get_code":{"code_sha256":"a03c334f626ed752"}},{"arxiv_id":"2401.10222","paper":"/paper/supervised-fine-tuning-in-turn-improves","title":"Supervised Fine-tuning in turn Improves Visual Foundation Models","date":"2024-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tencentarc/visft","path":"mmf/models/visft/segment_matcher.py","file_url":"https://github.com/tencentarc/visft/blob/HEAD/mmf/models/visft/segment_matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2401.02416","paper":"/paper/odin-a-single-model-for-2d-and-3d-perception","title":"ODIN: A Single Model for 2D and 3D Segmentation","date":"2024-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ayushjain1144/odin","path":"odin/modeling/matcher.py","file_url":"https://github.com/ayushjain1144/odin/blob/HEAD/odin/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2312.17118","paper":"/paper/fully-sparse-3d-panoptic-occupancy-prediction","title":"Fully Sparse 3D Occupancy Prediction","date":"2023-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mcg-nju/sparseocc","path":"models/matcher.py","file_url":"https://github.com/mcg-nju/sparseocc/blob/HEAD/models/matcher.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"483b6b8c81c0b6bb","mcp_get_code":{"code_sha256":"483b6b8c81c0b6bb"}},{"arxiv_id":"2312.09788","paper":"/paper/collaborating-foundation-models-for-domain","title":"Collaborating Foundation Models for Domain Generalized Semantic Segmentation","date":"2023-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yasserben/clouds","path":"clouds/modeling/matcher.py","file_url":"https://github.com/yasserben/clouds/blob/HEAD/clouds/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2312.09158","paper":"/paper/general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FoundationVision/GLEE","path":"projects/GLEE/glee/models/matcher.py","file_url":"https://github.com/FoundationVision/GLEE/blob/HEAD/projects/GLEE/glee/models/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2312.06630","paper":"/paper/tmt-vis-taxonomy-aware-multi-dataset-joint-1","title":"TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rkzheng99/TMT-VIS","path":"tmt/modeling/tmt_matcher.py","file_url":"https://github.com/rkzheng99/TMT-VIS/blob/HEAD/tmt/modeling/tmt_matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2312.04089","paper":"/paper/open-vocabulary-segmentation-with-semantic","title":"Open-Vocabulary Segmentation with Semantic-Assisted Calibration","date":"2023-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"workforai/scan","path":"scan/modeling/matcher.py","file_url":"https://github.com/workforai/scan/blob/HEAD/scan/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2312.03203","paper":"/paper/feature-3dgs-supercharging-3d-gaussian","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","date":"2023-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keloee/maskfield","path":"models/matcher.py","file_url":"https://github.com/keloee/maskfield/blob/HEAD/models/matcher.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b73525bcfb4b4e5a","mcp_get_code":{"code_sha256":"b73525bcfb4b4e5a"}},{"arxiv_id":"2312.02158","paper":"/paper/pasco-urban-3d-panoptic-scene-completion-with","title":"PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"astra-vision/PaSCo","path":"pasco/loss/matcher_sparse.py","file_url":"https://github.com/astra-vision/PaSCo/blob/HEAD/pasco/loss/matcher_sparse.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b73525bcfb4b4e5a","mcp_get_code":{"code_sha256":"b73525bcfb4b4e5a"}},{"arxiv_id":"2310.18954","paper":"/paper/mask-propagation-for-efficient-video-semantic-1","title":"Mask Propagation for Efficient Video Semantic Segmentation","date":"2023-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziplab/MPVSS","path":"mask2former/modeling/matcher.py","file_url":"https://github.com/ziplab/MPVSS/blob/HEAD/mask2former/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2310.00240","paper":"/paper/learning-mask-aware-clip-representations-for","title":"Learning Mask-aware CLIP Representations for Zero-Shot Segmentation","date":"2023-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiaosiyu1999/MAFT-Plus","path":"maft/modeling/matcher.py","file_url":"https://github.com/jiaosiyu1999/MAFT-Plus/blob/HEAD/maft/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2309.14338","paper":"/paper/3d-indoor-instance-segmentation-in-an-open-1","title":"3D Indoor Instance Segmentation in an Open-World","date":"2023-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aminebdj/3D-OWIS","path":"models/matcher.py","file_url":"https://github.com/aminebdj/3D-OWIS/blob/HEAD/models/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2309.01692","paper":"/paper/mask-attention-free-transformer-for-3d","title":"Mask-Attention-Free Transformer for 3D Instance Segmentation","date":"2023-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/mask-attention-free-transformer","path":"maft/model/loss.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"89f8d423e0baf041","mcp_get_code":{"code_sha256":"89f8d423e0baf041"}},{"arxiv_id":"2308.16632","paper":"/paper/3d-stmn-dependency-driven-superpoint-text","title":"3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation","date":"2023-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sosppxo/3d-stmn","path":"stmn/model/loss.py","file_url":"https://github.com/sosppxo/3d-stmn/blob/HEAD/stmn/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"89f8d423e0baf041","mcp_get_code":{"code_sha256":"89f8d423e0baf041"}},{"arxiv_id":"2308.08544","paper":"/paper/mevis-a-large-scale-benchmark-for-video","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","date":"2023-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"henghuiding/MeViS","path":"lmpm/modeling/vita_matcher.py","file_url":"https://github.com/henghuiding/MeViS/blob/HEAD/lmpm/modeling/vita_matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2308.06531","paper":"/paper/segprompt-boosting-open-world-segmentation","title":"SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning","date":"2023-08-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aim-uofa/segprompt","path":"mask2former/modeling/matcher.py","file_url":"https://github.com/aim-uofa/segprompt/blob/HEAD/mask2former/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2306.15670","paper":"/paper/symphonize-3d-semantic-scene-completion-with","title":"Symphonize 3D Semantic Scene Completion with Contextual Instance Queries","date":"2023-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/symphonies","path":"maskdino/models/matcher.py","file_url":"https://github.com/hustvl/symphonies/blob/HEAD/maskdino/models/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2306.11087","paper":"/paper/primitive-generation-and-semantic-related-1","title":"Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation","date":"2023-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heshuting555/PADing","path":"PADing/modeling/matcher.py","file_url":"https://github.com/heshuting555/PADing/blob/HEAD/PADing/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2306.09347","paper":"/paper/segment-any-point-cloud-sequences-by","title":"Segment Any Point Cloud Sequences by Distilling Vision Foundation Models","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEA-Research/OpenSeeD","path":"openseed/modules/matcher.py","file_url":"https://github.com/IDEA-Research/OpenSeeD/blob/HEAD/openseed/modules/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2306.07404","paper":"/paper/compositor-bottom-up-clustering-and-1","title":"Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tacju/compositor","path":"Compositor_Mask2Former/compositor/modeling/matcher.py","file_url":"https://github.com/tacju/compositor/blob/HEAD/Compositor_Mask2Former/compositor/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2306.03437","paper":"/paper/dformer-diffusion-guided-transformer-for","title":"DFormer: Diffusion-guided Transformer for Universal Image Segmentation","date":"2023-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cp3wan/dformer","path":"dformer/modeling/matcher.py","file_url":"https://github.com/cp3wan/dformer/blob/HEAD/dformer/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2305.16133","paper":"/paper/ovo-open-vocabulary-occupancy","title":"OVO: Open-Vocabulary Occupancy","date":"2023-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dzcgaara/OVO","path":"ovo/loss/matcher.py","file_url":"https://github.com/dzcgaara/OVO/blob/HEAD/ovo/loss/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"690e5487ce07509a","mcp_get_code":{"code_sha256":"690e5487ce07509a"}},{"arxiv_id":"2303.17386","paper":"/paper/complementary-random-masking-for-rgb-thermal","title":"Complementary Random Masking for RGB-Thermal Semantic Segmentation","date":"2023-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UkcheolShin/CRM_RGBTSeg","path":"models/mask2former/matcher.py","file_url":"https://github.com/UkcheolShin/CRM_RGBTSeg/blob/HEAD/models/mask2former/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2303.15904","paper":"/paper/mask-free-video-instance-segmentation","title":"Mask-Free Video Instance Segmentation","date":"2023-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"syscv/maskfreevis","path":"mask2former/modeling/matcher.py","file_url":"https://github.com/syscv/maskfreevis/blob/HEAD/mask2former/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"28180c8c241c50da","mcp_get_code":{"code_sha256":"28180c8c241c50da"}},{"arxiv_id":"2303.08594","paper":"/paper/fastinst-a-simple-query-based-model-for-real","title":"FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation","date":"2023-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junjiehe96/fastinst","path":"fastinst/modeling/matcher.py","file_url":"https://github.com/junjiehe96/fastinst/blob/HEAD/fastinst/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2302.12242","paper":"/paper/side-adapter-network-for-open-vocabulary","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","date":"2023-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"blumenstiel/SAN-MESS","path":"san/model/matcher.py","file_url":"https://github.com/blumenstiel/SAN-MESS/blob/HEAD/san/model/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2211.16799","paper":"/paper/nope-sac-neural-one-plane-ransac-for-sparse","title":"NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction","date":"2022-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"icetttb/nopesac","path":"NopeSAC_Net/modeling/matcher.py","file_url":"https://github.com/icetttb/nopesac/blob/HEAD/NopeSAC_Net/modeling/matcher.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b73525bcfb4b4e5a","mcp_get_code":{"code_sha256":"b73525bcfb4b4e5a"}},{"arxiv_id":"2211.06220","paper":"/paper/oneformer-one-transformer-to-rule-universal","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","date":"2022-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SHI-Labs/OneFormer","path":"oneformer/modeling/matcher.py","file_url":"https://github.com/SHI-Labs/OneFormer/blob/HEAD/oneformer/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2210.03105","paper":"/paper/mask3d-for-3d-semantic-instance-segmentation","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jonasschult/mask3d","path":"models/matcher.py","file_url":"https://github.com/jonasschult/mask3d/blob/HEAD/models/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2206.04403","paper":"/paper/vita-video-instance-segmentation-via-object","title":"VITA: Video Instance Segmentation via Object Token Association","date":"2022-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sukjunhwang/vita","path":"vita/modeling/vita_matcher.py","file_url":"https://github.com/sukjunhwang/vita/blob/HEAD/vita/modeling/vita_matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2203.04187","paper":"/paper/mlseg-image-and-video-segmentation-as-multi","title":"RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation","date":"2022-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/Mask2Former","path":"mask2former/modeling/matcher.py","file_url":"https://github.com/facebookresearch/Mask2Former/blob/HEAD/mask2former/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2203.03605","paper":"/paper/dino-detr-with-improved-denoising-anchor-1","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","date":"2022-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEACVR/MaskDINO","path":"maskdino/modeling/matcher.py","file_url":"https://github.com/IDEACVR/MaskDINO/blob/HEAD/maskdino/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2112.10764","paper":"/paper/mask2former-for-video-instance-segmentation","title":"Mask2Former for Video Instance Segmentation","date":"2021-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nihalsid/mask2former","path":"mask2former/modeling/matcher.py","file_url":"https://github.com/nihalsid/mask2former/blob/HEAD/mask2former/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"2112.01527","paper":"/paper/masked-attention-mask-transformer-for","title":"Masked-attention Mask Transformer for Universal Image Segmentation","date":"2021-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DdeGeus/Mask2Former-IBS","path":"mask2former/modeling/matcher.py","file_url":"https://github.com/DdeGeus/Mask2Former-IBS/blob/HEAD/mask2former/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"aaai_28408","paper":null,"title":"arXiv:aaai_28408","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"sosppxo/3D-STMN","path":"stmn/model/loss.py","file_url":"https://github.com/sosppxo/3D-STMN/blob/HEAD/stmn/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"89f8d423e0baf041","mcp_get_code":{"code_sha256":"89f8d423e0baf041"}},{"arxiv_id":"aaai_25335","paper":null,"title":"arXiv:aaai_25335","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"sunjiahao1999/SPFormer","path":"spformer/model/loss.py","file_url":"https://github.com/sunjiahao1999/SPFormer/blob/HEAD/spformer/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"89f8d423e0baf041","mcp_get_code":{"code_sha256":"89f8d423e0baf041"}},{"arxiv_id":"Zhang_Uni-3D_A_Universal_Model_for_Panoptic_3D_Scene_Reconstruction_ICCV_2023_paper","paper":null,"title":"arXiv:Zhang_Uni-3D_A_Universal_Model_for_Panoptic_3D_Scene_Reconstruction_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"mlpc-ucsd/Uni-3D","path":"uni_3d/modeling/matcher.py","file_url":"https://github.com/mlpc-ucsd/Uni-3D/blob/HEAD/uni_3d/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"Zhang_FreePoint_Unsupervised_Point_Cloud_Instance_Segmentation_CVPR_2024_paper","paper":null,"title":"arXiv:Zhang_FreePoint_Unsupervised_Point_Cloud_Instance_Segmentation_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zzk273/FreePoint","path":"models/matcher_freepoint.py","file_url":"https://github.com/zzk273/FreePoint/blob/HEAD/models/matcher_freepoint.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"Li_Mask_DINO_Towards_a_Unified_Transformer-Based_Framework_for_Object_Detection_CVPR_2023_paper","paper":null,"title":"arXiv:Li_Mask_DINO_Towards_a_Unified_Transformer-Based_Framework_for_Object_Detection_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"IDEA-Research/MaskDINO","path":"maskdino/modeling/matcher.py","file_url":"https://github.com/IDEA-Research/MaskDINO/blob/HEAD/maskdino/modeling/matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"Heo_A_Generalized_Framework_for_Video_Instance_Segmentation_CVPR_2023_paper","paper":null,"title":"arXiv:Heo_A_Generalized_Framework_for_Video_Instance_Segmentation_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"miranheo/GenVIS","path":"genvis/modeling/genvis_matcher.py","file_url":"https://github.com/miranheo/GenVIS/blob/HEAD/genvis/modeling/genvis_matcher.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc2cb481a75c370d","mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"arxiv_id":"03570","paper":null,"title":"arXiv:03570","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"MCG-NJU/SparseOcc","path":"models/matcher.py","file_url":"https://github.com/MCG-NJU/SparseOcc/blob/HEAD/models/matcher.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"483b6b8c81c0b6bb","mcp_get_code":{"code_sha256":"483b6b8c81c0b6bb"}}]}