{"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":"/paper/uniref-segment-every-reference-object-in","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","arxiv_id":"2312.15715","date":"2023-12-25","proceeding":null,"authors":["Jiannan Wu","Yi Jiang","Bin Yan","Huchuan Lu","Zehuan Yuan","Ping Luo"],"abstract":"The reference-based object segmentation tasks, namely referring image segmentation (RIS), few-shot image segmentation (FSS), referring video object segmentation (RVOS), and video object segmentation (VOS), aim to segment a specific object by utilizing either language or annotated masks as references. Despite significant progress in each respective field, current methods are task-specifically designed and developed in different directions, which hinders the activation of multi-task capabilities for these tasks. In this work, we end the current fragmented situation and propose UniRef++ to unify the four reference-based object segmentation tasks with a single architecture. At the heart of our approach is the proposed UniFusion module which performs multiway-fusion for handling different tasks with respect to their specified references. And a unified Transformer architecture is then adopted for achieving instance-level segmentation. With the unified designs, UniRef++ can be jointly trained on a broad range of benchmarks and can flexibly complete multiple tasks at run-time by specifying the corresponding references. We evaluate our unified models on various benchmarks. Extensive experimental results indicate that our proposed UniRef++ achieves state-of-the-art performance on RIS and RVOS, and performs competitively on FSS and VOS with a parameter-shared network. Moreover, we showcase that the proposed UniFusion module could be easily incorporated into the current advanced foundation model SAM and obtain satisfactory results with parameter-efficient finetuning. Codes and models are available at \\url{https://github.com/FoundationVision/UniRef}.","url_abs":"https://arxiv.org/abs/2312.15715v1","url_pdf":"https://arxiv.org/pdf/2312.15715v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"uniref-segment-every-reference-object-in","repo_url":"https://github.com/foundationvision/uniref","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"uniref-segment-every-reference-object-in","repo_url":"https://github.com/FaceOnLive/Realtime-Background-Changer-SDK-Android","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"referring-video-object-segmentation","task_name":"Referring Video Object Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sam","method_name":"SAM"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vos","method_name":"VOS"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-expression-segmentation-on-refer-1","task":"Referring Expression Segmentation","dataset":"Refer-YouTube-VOS (2021 public validation)","model":"UniRef++-L","rank_in_archive_order":12,"of":33,"metrics":{"F":"69.0","J":"64.8","J&F":"66.9"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2312.15715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15715"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/foundationvision/uniref","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FaceOnLive/Realtime-Background-Changer-SDK-Android","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":5,"ran_honours":1,"ran_fixture":2},"by_repo_kind":{"official":{"samples":9,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"29dbbaafa4be18e1","entry":"aligned_bilinear","repo":"foundationvision/uniref","repo_kind":"official","path":"projects/UniRef/uniref/models/ddetrs.py","file_url":"https://github.com/foundationvision/uniref/blob/HEAD/projects/UniRef/uniref/models/ddetrs.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"29dbbaafa4be18e1"}},{"code_sha256_prefix":"8243ac0c601917dc","entry":"bounding_box","repo":"foundationvision/uniref","repo_kind":"official","path":"projects/UniRef/uniref/uniref.py","file_url":"https://github.com/foundationvision/uniref/blob/HEAD/projects/UniRef/uniref/uniref.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8243ac0c601917dc"}},{"code_sha256_prefix":"ed1a308adb65f645","entry":"compute_locations","repo":"foundationvision/uniref","repo_kind":"official","path":"projects/UniRef/uniref/models/ddetrs.py","file_url":"https://github.com/foundationvision/uniref/blob/HEAD/projects/UniRef/uniref/models/ddetrs.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed1a308adb65f645"}},{"code_sha256_prefix":"4de0dcaf9f33183b","entry":"compute_mask_iou","repo":"foundationvision/uniref","repo_kind":"official","path":"projects/UniRef/uniref/models/uniref_sam.py","file_url":"https://github.com/foundationvision/uniref/blob/HEAD/projects/UniRef/uniref/models/uniref_sam.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4de0dcaf9f33183b"}},{"code_sha256_prefix":"286983a8483318b8","entry":"concat_mask_dict_features","repo":"foundationvision/uniref","repo_kind":"official","path":"projects/UniRef/uniref/uniref.py","file_url":"https://github.com/foundationvision/uniref/blob/HEAD/projects/UniRef/uniref/uniref.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"286983a8483318b8"}},{"code_sha256_prefix":"a1c2083ec2eaeb22","entry":"dice_loss","repo":"foundationvision/uniref","repo_kind":"official","path":"projects/UniRef/uniref/models/uniref_sam.py","file_url":"https://github.com/foundationvision/uniref/blob/HEAD/projects/UniRef/uniref/models/uniref_sam.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1c2083ec2eaeb22"}},{"code_sha256_prefix":"46f34dc9f9a94b67","entry":"parse_dynamic_params","repo":"foundationvision/uniref","repo_kind":"official","path":"projects/UniRef/uniref/models/ddetrs.py","file_url":"https://github.com/foundationvision/uniref/blob/HEAD/projects/UniRef/uniref/models/ddetrs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46f34dc9f9a94b67"}},{"code_sha256_prefix":"e28a878991e1e696","entry":"sigmoid_ce_loss","repo":"foundationvision/uniref","repo_kind":"official","path":"projects/UniRef/uniref/models/uniref_sam.py","file_url":"https://github.com/foundationvision/uniref/blob/HEAD/projects/UniRef/uniref/models/uniref_sam.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e28a878991e1e696"}},{"code_sha256_prefix":"6bc62d34967e2917","entry":"unfold_wo_center","repo":"foundationvision/uniref","repo_kind":"official","path":"projects/UniRef/uniref/uniref.py","file_url":"https://github.com/foundationvision/uniref/blob/HEAD/projects/UniRef/uniref/uniref.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6bc62d34967e2917"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}