{"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/hierarchy-based-image-embeddings-for-semantic","title":"Hierarchy-based Image Embeddings for Semantic Image Retrieval","arxiv_id":"1809.09924","date":"2018-09-26","proceeding":null,"authors":["Björn Barz","Joachim Denzler"],"abstract":"Deep neural networks trained for classification have been found to learn\npowerful image representations, which are also often used for other tasks such\nas comparing images w.r.t. their visual similarity. However, visual similarity\ndoes not imply semantic similarity. In order to learn semantically\ndiscriminative features, we propose to map images onto class embeddings whose\npair-wise dot products correspond to a measure of semantic similarity between\nclasses. Such an embedding does not only improve image retrieval results, but\ncould also facilitate integrating semantics for other tasks, e.g., novelty\ndetection or few-shot learning. We introduce a deterministic algorithm for\ncomputing the class centroids directly based on prior world-knowledge encoded\nin a hierarchy of classes such as WordNet. Experiments on CIFAR-100, NABirds,\nand ImageNet show that our learned semantic image embeddings improve the\nsemantic consistency of image retrieval results by a large margin.","url_abs":"http://arxiv.org/abs/1809.09924v4","url_pdf":"http://arxiv.org/pdf/1809.09924v4.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":"hierarchy-based-image-embeddings-for-semantic","repo_url":"https://github.com/cvjena/semantic-embeddings","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"novelty-detection","task_name":"Novelty Detection"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.09924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.09924"}},"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/cvjena/semantic-embeddings","reach":null}],"summary":{"ran_fixture":2,"ran_violates":1},"by_repo_kind":{},"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":"1f726f5ea616424c","entry":"euclidean_embedding","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"1f726f5ea616424c"}},{"code_sha256_prefix":"234d5f2d97a6f36f","entry":"sim_approx","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"234d5f2d97a6f36f"}},{"code_sha256_prefix":"f83a7b7243eb16a4","entry":"unitsphere_embedding","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":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f83a7b7243eb16a4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}