{"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/emergent-visual-semantic-hierarchies-in-image","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","arxiv_id":"2407.08521","date":"2024-07-11","proceeding":null,"authors":["Morris Alper","Hadar Averbuch-Elor"],"abstract":"While recent vision-and-language models (VLMs) like CLIP are a powerful tool for analyzing text and images in a shared semantic space, they do not explicitly model the hierarchical nature of the set of texts which may describe an image. Conversely, existing multimodal hierarchical representation learning methods require costly training from scratch, failing to leverage the knowledge encoded by state-of-the-art multimodal foundation models. In this work, we study the knowledge of existing foundation models, finding that they exhibit emergent understanding of visual-semantic hierarchies despite not being directly trained for this purpose. We propose the Radial Embedding (RE) framework for probing and optimizing hierarchical understanding, and contribute the HierarCaps dataset, a benchmark facilitating the study of hierarchical knowledge in image--text representations, constructed automatically via large language models. Our results show that foundation VLMs exhibit zero-shot hierarchical understanding, surpassing the performance of prior models explicitly designed for this purpose. Furthermore, we show that foundation models may be better aligned to hierarchical reasoning via a text-only fine-tuning phase, while retaining pretraining knowledge.","url_abs":"https://arxiv.org/abs/2407.08521v2","url_pdf":"https://arxiv.org/pdf/2407.08521v2.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":"emergent-visual-semantic-hierarchies-in-image","repo_url":"https://github.com/TAU-VAILab/hierarcaps","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"hierarchical-text-image-matching","task_name":"Hierarchical Text-Image Matching"},{"task_slug":"lexical-entailment","task_name":"Lexical Entailment"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[{"slug":"hierarcaps","name":"HierarCaps","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.08521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08521"}},"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/TAU-VAILab/hierarcaps","reach":{"status":"ok"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"7031da4ad5b9ac55","entry":"calculate_Ro","repo":"TAU-VAILab/hierarcaps","repo_kind":"official","path":"code/evaluation/hierarchical_retrieval.py","file_url":"https://github.com/TAU-VAILab/hierarcaps/blob/HEAD/code/evaluation/hierarchical_retrieval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7031da4ad5b9ac55"}},{"code_sha256_prefix":"7e5b0f4a6dffc0c3","entry":"calculate_Ro_multi","repo":"TAU-VAILab/hierarcaps","repo_kind":"official","path":"code/evaluation/hierarchical_retrieval.py","file_url":"https://github.com/TAU-VAILab/hierarcaps/blob/HEAD/code/evaluation/hierarchical_retrieval.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":"7e5b0f4a6dffc0c3"}},{"code_sha256_prefix":"1adbff310ed035a5","entry":"fn2id","repo":"TAU-VAILab/hierarcaps","repo_kind":"official","path":"code/evaluation/hierarchical_retrieval.py","file_url":"https://github.com/TAU-VAILab/hierarcaps/blob/HEAD/code/evaluation/hierarchical_retrieval.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":"1adbff310ed035a5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}