{"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/instructseg-unifying-instructed-visual","title":"InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models","arxiv_id":"2412.14006","date":"2024-12-18","proceeding":null,"authors":["Cong Wei","Yujie Zhong","Haoxian Tan","Yingsen Zeng","Yong liu","Zheng Zhao","Yujiu Yang"],"abstract":"Boosted by Multi-modal Large Language Models (MLLMs), text-guided universal segmentation models for the image and video domains have made rapid progress recently. However, these methods are often developed separately for specific domains, overlooking the similarities in task settings and solutions across these two areas. In this paper, we define the union of referring segmentation and reasoning segmentation at both the image and video levels as Instructed Visual Segmentation (IVS). Correspondingly, we propose InstructSeg, an end-to-end segmentation pipeline equipped with MLLMs for IVS. Specifically, we employ an object-aware video perceiver to extract temporal and object information from reference frames, facilitating comprehensive video understanding. Additionally, we introduce vision-guided multi-granularity text fusion to better integrate global and detailed text information with fine-grained visual guidance. By leveraging multi-task and end-to-end training, InstructSeg demonstrates superior performance across diverse image and video segmentation tasks, surpassing both segmentation specialists and MLLM-based methods with a single model. Our code is available at https://github.com/congvvc/InstructSeg.","url_abs":"https://arxiv.org/abs/2412.14006v1","url_pdf":"https://arxiv.org/pdf/2412.14006v1.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":"instructseg-unifying-instructed-visual","repo_url":"https://github.com/congvvc/instructseg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"reasoning-segmentation","task_name":"Reasoning Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"universal-segmentation","task_name":"Universal Segmentation"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.14006","atlas_url":"https://app.syntology.ai/?focus=2412.14006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14006"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/congvvc/instructseg","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":3,"ran_violates":1,"ran":5,"unverified":4},"by_repo_kind":{"official":{"samples":14,"ran":10,"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":"144d10b49baeb8a6","entry":"window_partition","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/model/mask_encoder/swin_trans.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/model/mask_encoder/swin_trans.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"4d75570b4e91d0b4","entry":"FeedForward","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/model/language_model/ovp.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/model/language_model/ovp.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4d75570b4e91d0b4"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/model/language_model/ovp.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/model/language_model/ovp.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"592b3c1a88f93d7c","entry":"expand2square","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/model/mipha/mm_utils.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/model/mipha/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"592b3c1a88f93d7c"}},{"code_sha256_prefix":"520d771d01a3c5ef","entry":"find_linear_layers","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/train/merge_lora_weights_and_save_hf_model.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/train/merge_lora_weights_and_save_hf_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"520d771d01a3c5ef"}},{"code_sha256_prefix":"231df0d16f40deaf","entry":"get_mask_from_json","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/model/datasets_mapper/IVS_mapper.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/model/datasets_mapper/IVS_mapper.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"231df0d16f40deaf"}},{"code_sha256_prefix":"c3ee9d07c900dd55","entry":"load_image_from_base64","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/model/mipha/mm_utils.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/model/mipha/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c3ee9d07c900dd55"}},{"code_sha256_prefix":"50b4f58ac51e3844","entry":"load_revos_json","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/datasets/ytvos.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/datasets/ytvos.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"50b4f58ac51e3844"}},{"code_sha256_prefix":"9e11de9f538299ab","entry":"parse_args","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/train/merge_lora_weights_and_save_hf_model.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/train/merge_lora_weights_and_save_hf_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9e11de9f538299ab"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/model/mask_encoder/swin_trans.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/model/mask_encoder/swin_trans.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"670eda77b277eb8a","entry":"build_swin_t","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/model/mask_encoder/swin_trans.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/model/mask_encoder/swin_trans.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"670eda77b277eb8a"}},{"code_sha256_prefix":"bbe128f6633ed802","entry":"check_shape","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/model/language_model/einops_exts.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/model/language_model/einops_exts.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bbe128f6633ed802"}},{"code_sha256_prefix":"ee5e474262386435","entry":"filter_empty_instances_soft","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/datasets/ytvos.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/datasets/ytvos.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ee5e474262386435"}},{"code_sha256_prefix":"344dff4791fd1381","entry":"process_images","repo":"congvvc/instructseg","repo_kind":"official","path":"instructseg/model/mipha/mm_utils.py","file_url":"https://github.com/congvvc/instructseg/blob/HEAD/instructseg/model/mipha/mm_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"344dff4791fd1381"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}