{"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/efficient-end-to-end-learning-for-quantizable","title":"Efficient end-to-end learning for quantizable representations","arxiv_id":"1805.05809","date":"2018-05-15","proceeding":"ICML 2018 7","authors":["Yeonwoo Jeong","Hyun Oh Song"],"abstract":"Embedding representation learning via neural networks is at the core\nfoundation of modern similarity based search. While much effort has been put in\ndeveloping algorithms for learning binary hamming code representations for\nsearch efficiency, this still requires a linear scan of the entire dataset per\neach query and trades off the search accuracy through binarization. To this\nend, we consider the problem of directly learning a quantizable embedding\nrepresentation and the sparse binary hash code end-to-end which can be used to\nconstruct an efficient hash table not only providing significant search\nreduction in the number of data but also achieving the state of the art search\naccuracy outperforming previous state of the art deep metric learning methods.\nWe also show that finding the optimal sparse binary hash code in a mini-batch\ncan be computed exactly in polynomial time by solving a minimum cost flow\nproblem. Our results on Cifar-100 and on ImageNet datasets show the state of\nthe art search accuracy in precision@k and NMI metrics while providing up to\n98X and 478X search speedup respectively over exhaustive linear search. The\nsource code is available at\nhttps://github.com/maestrojeong/Deep-Hash-Table-ICML18","url_abs":"http://arxiv.org/abs/1805.05809v3","url_pdf":"http://arxiv.org/pdf/1805.05809v3.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":"efficient-end-to-end-learning-for-quantizable","repo_url":"https://github.com/maestrojeong/Deep-Hash-Table-ICML18","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"binarization","task_name":"Binarization"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.05809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.05809"}},"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/maestrojeong/Deep-Hash-Table-ICML18","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"e5956ff53e94e9c7","entry":"imagenet_image_processor","repo":"maestrojeong/Deep-Hash-Table-ICML18","repo_kind":"official","path":"process/imagenet32_process.py","file_url":"https://github.com/maestrojeong/Deep-Hash-Table-ICML18/blob/HEAD/process/imagenet32_process.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":"e5956ff53e94e9c7"}},{"code_sha256_prefix":"43812b24139be790","entry":"pairwise_distance_w_obj1","repo":"maestrojeong/Deep-Hash-Table-ICML18","repo_kind":"official","path":"tfops/hash_dist.py","file_url":"https://github.com/maestrojeong/Deep-Hash-Table-ICML18/blob/HEAD/tfops/hash_dist.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":"43812b24139be790"}},{"code_sha256_prefix":"a8e80fc083f58319","entry":"pairwise_similarity_w_obj1","repo":"maestrojeong/Deep-Hash-Table-ICML18","repo_kind":"official","path":"tfops/hash_dist.py","file_url":"https://github.com/maestrojeong/Deep-Hash-Table-ICML18/blob/HEAD/tfops/hash_dist.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":"a8e80fc083f58319"}},{"code_sha256_prefix":"588b7834dcd00712","entry":"pairwise_similarity_w_obj2","repo":"maestrojeong/Deep-Hash-Table-ICML18","repo_kind":"official","path":"tfops/hash_dist.py","file_url":"https://github.com/maestrojeong/Deep-Hash-Table-ICML18/blob/HEAD/tfops/hash_dist.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":"588b7834dcd00712"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}