{"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/deep-triplet-quantization","title":"Deep Triplet Quantization","arxiv_id":"1902.00153","date":"2019-02-01","proceeding":null,"authors":["Bin Liu","Yue Cao","Mingsheng Long","Jian-Min Wang","Jingdong Wang"],"abstract":"Deep hashing establishes efficient and effective image retrieval by\nend-to-end learning of deep representations and hash codes from similarity\ndata. We present a compact coding solution, focusing on deep learning to\nquantization approach that has shown superior performance over hashing\nsolutions for similarity retrieval. We propose Deep Triplet Quantization (DTQ),\na novel approach to learning deep quantization models from the similarity\ntriplets. To enable more effective triplet training, we design a new triplet\nselection approach, Group Hard, that randomly selects hard triplets in each\nimage group. To generate compact binary codes, we further apply a triplet\nquantization with weak orthogonality during triplet training. The quantization\nloss reduces the codebook redundancy and enhances the quantizability of deep\nrepresentations through back-propagation. Extensive experiments demonstrate\nthat DTQ can generate high-quality and compact binary codes, which yields\nstate-of-the-art image retrieval performance on three benchmark datasets,\nNUS-WIDE, CIFAR-10, and MS-COCO.","url_abs":"http://arxiv.org/abs/1902.00153v1","url_pdf":"http://arxiv.org/pdf/1902.00153v1.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":"deep-triplet-quantization","repo_url":"https://github.com/thulab/DeepHash","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-hashing","task_name":"Deep Hashing"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-nus-wide","task":"Image Retrieval","dataset":"NUS-WIDE","model":"DTQ","rank_in_archive_order":1,"of":1,"metrics":{"MAP":"0.801"},"uses_additional_data":false},{"leaderboard":"/sota/quantization-on-cifar-10","task":"Quantization","dataset":"CIFAR-10","model":"DTQ","rank_in_archive_order":2,"of":2,"metrics":{"MAP":"0.792"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.00153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.00153"}},"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/thulab/DeepHash","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"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":"ca7c0db08dbf8623","entry":"euclidean2","repo":"thulab/DeepHash","repo_kind":"listed","path":"DeepHash/distance/npversion.py","file_url":"https://github.com/thulab/DeepHash/blob/HEAD/DeepHash/distance/npversion.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":"ca7c0db08dbf8623"}},{"code_sha256_prefix":"fe1f6d53c33c41d9","entry":"hamming_precision","repo":"thulab/DeepHash","repo_kind":"listed","path":"DeepHash/evaluation/load_and_predict.py","file_url":"https://github.com/thulab/DeepHash/blob/HEAD/DeepHash/evaluation/load_and_predict.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":"fe1f6d53c33c41d9"}},{"code_sha256_prefix":"5887d2f606711347","entry":"mean_average_precision","repo":"thulab/DeepHash","repo_kind":"listed","path":"DeepHash/evaluation/load_and_predict.py","file_url":"https://github.com/thulab/DeepHash/blob/HEAD/DeepHash/evaluation/load_and_predict.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":"5887d2f606711347"}},{"code_sha256_prefix":"059794905f42414c","entry":"norm","repo":"thulab/DeepHash","repo_kind":"listed","path":"DeepHash/distance/npversion.py","file_url":"https://github.com/thulab/DeepHash/blob/HEAD/DeepHash/distance/npversion.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":"059794905f42414c"}},{"code_sha256_prefix":"aeeb3c7dc6c8e670","entry":"norm","repo":"thulab/DeepHash","repo_kind":"listed","path":"DeepHash/distance/tfversion.py","file_url":"https://github.com/thulab/DeepHash/blob/HEAD/DeepHash/distance/tfversion.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":"aeeb3c7dc6c8e670"}},{"code_sha256_prefix":"9655a5f08f5b0f85","entry":"normed","repo":"thulab/DeepHash","repo_kind":"listed","path":"DeepHash/distance/npversion.py","file_url":"https://github.com/thulab/DeepHash/blob/HEAD/DeepHash/distance/npversion.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":"9655a5f08f5b0f85"}},{"code_sha256_prefix":"9901bdfb8b1ece6a","entry":"precision","repo":"thulab/DeepHash","repo_kind":"listed","path":"DeepHash/evaluation/load_and_predict.py","file_url":"https://github.com/thulab/DeepHash/blob/HEAD/DeepHash/evaluation/load_and_predict.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":"9901bdfb8b1ece6a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}