{"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/pink-unveiling-the-power-of-referential","title":"Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs","arxiv_id":"2310.00582","date":"2023-10-01","proceeding":"CVPR 2024 1","authors":["Shiyu Xuan","Qingpei Guo","Ming Yang","Shiliang Zhang"],"abstract":"Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks is still limited. To address this issue, this paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. Specifically, we present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. A self-consistent bootstrapping method is also introduced to extend existing dense object annotations into high-quality referring-expression-bounding-box pairs. These methods enable the generation of high-quality instruction data which includes a wide range of fundamental abilities essential for fine-grained image perception. Moreover, we argue that the visual encoder should be tuned during instruction tuning to mitigate the gap between full image perception and fine-grained image perception. Experimental results demonstrate the superior performance of our method. For instance, our model exhibits a 5.2% accuracy improvement over Qwen-VL on GQA and surpasses the accuracy of Kosmos-2 by 24.7% on RefCOCO_val. We have also attained the top rank on the leaderboard of MMBench. This promising performance is achieved by training on only publicly available data, making it easily reproducible. The models, datasets, and codes are publicly available at https://github.com/SY-Xuan/Pink.","url_abs":"https://arxiv.org/abs/2310.00582v3","url_pdf":"https://arxiv.org/pdf/2310.00582v3.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":"pink-unveiling-the-power-of-referential","repo_url":"https://github.com/sy-xuan/pink","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"referring-expression","task_name":"Referring Expression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.00582","atlas_url":"https://app.syntology.ai/?focus=2310.00582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00582"}},"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/sy-xuan/pink","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"ran":1,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"ee1020522a070904","entry":"expand2square","repo":"sy-xuan/pink","repo_kind":"official","path":"pink/eval/model_gqa.py","file_url":"https://github.com/sy-xuan/pink/blob/HEAD/pink/eval/model_gqa.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ee1020522a070904"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"sy-xuan/pink","repo_kind":"official","path":"pink/eval/model_gqa.py","file_url":"https://github.com/sy-xuan/pink/blob/HEAD/pink/eval/model_gqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"sy-xuan/pink","repo_kind":"official","path":"pink/eval/model_gqa.py","file_url":"https://github.com/sy-xuan/pink/blob/HEAD/pink/eval/model_gqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"8f1a44ab20956301","entry":"normalize_word","repo":"sy-xuan/pink","repo_kind":"official","path":"pink/eval/model_vqav2.py","file_url":"https://github.com/sy-xuan/pink/blob/HEAD/pink/eval/model_vqav2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f1a44ab20956301"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}