{"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/hgclip-exploring-vision-language-models-with-1","title":"HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding","arxiv_id":"2311.14064","date":"2023-11-23","proceeding":null,"authors":["Peng Xia","Xingtong Yu","Ming Hu","Lie Ju","Zhiyong Wang","Peibo Duan","ZongYuan Ge"],"abstract":"Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revealing limitations in complex scenarios. Recent studies integrating Vision-Language Models (VLMs) with class hierarchies have shown promise, yet they fall short of fully exploiting the hierarchical relationships. These efforts are constrained by their inability to perform effectively across varied granularity of categories. To tackle this issue, we propose a novel framework (HGCLIP) that effectively combines CLIP with a deeper exploitation of the Hierarchical class structure via Graph representation learning. We explore constructing the class hierarchy into a graph, with its nodes representing the textual or image features of each category. After passing through a graph encoder, the textual features incorporate hierarchical structure information, while the image features emphasize class-aware features derived from prototypes through the attention mechanism. Our approach demonstrates significant improvements on 11 diverse visual recognition benchmarks. Our codes are fully available at https://github.com/richard-peng-xia/HGCLIP.","url_abs":"https://arxiv.org/abs/2311.14064v3","url_pdf":"https://arxiv.org/pdf/2311.14064v3.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":"hgclip-exploring-vision-language-models-with-1","repo_url":"https://github.com/richard-peng-xia/HGCLIP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"fine-grained-visual-recognition","task_name":"Fine-Grained Visual Recognition"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.14064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14064"}},"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/richard-peng-xia/HGCLIP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"richard-peng-xia/HGCLIP","repo_kind":"official","path":"hgclip/clip/simple_tokenizer.py","file_url":"https://github.com/richard-peng-xia/HGCLIP/blob/HEAD/hgclip/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"richard-peng-xia/HGCLIP","repo_kind":"official","path":"hgclip/clip/simple_tokenizer.py","file_url":"https://github.com/richard-peng-xia/HGCLIP/blob/HEAD/hgclip/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"richard-peng-xia/HGCLIP","repo_kind":"official","path":"hgclip/clip/simple_tokenizer.py","file_url":"https://github.com/richard-peng-xia/HGCLIP/blob/HEAD/hgclip/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"3cba061e8afa772a","entry":"acc","repo":"richard-peng-xia/HGCLIP","repo_kind":"official","path":"hgclip/utils/metrics.py","file_url":"https://github.com/richard-peng-xia/HGCLIP/blob/HEAD/hgclip/utils/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3cba061e8afa772a"}},{"code_sha256_prefix":"77beb4951c2eb25f","entry":"build_model","repo":"richard-peng-xia/HGCLIP","repo_kind":"official","path":"hgclip/clip/model.py","file_url":"https://github.com/richard-peng-xia/HGCLIP/blob/HEAD/hgclip/clip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"77beb4951c2eb25f"}},{"code_sha256_prefix":"fbf8c0143d9c48e3","entry":"load","repo":"richard-peng-xia/HGCLIP","repo_kind":"official","path":"hgclip/clip/clip.py","file_url":"https://github.com/richard-peng-xia/HGCLIP/blob/HEAD/hgclip/clip/clip.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbf8c0143d9c48e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}