{"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/generalizable-mixed-precision-quantization","title":"Generalizable Mixed-Precision Quantization via Attribution Rank Preservation","arxiv_id":"2108.02720","date":"2021-08-05","proceeding":"ICCV 2021 10","authors":["Ziwei Wang","Han Xiao","Jiwen Lu","Jie zhou"],"abstract":"In this paper, we propose a generalizable mixed-precision quantization (GMPQ) method for efficient inference. Conventional methods require the consistency of datasets for bitwidth search and model deployment to guarantee the policy optimality, leading to heavy search cost on challenging largescale datasets in realistic applications. On the contrary, our GMPQ searches the mixed-quantization policy that can be generalized to largescale datasets with only a small amount of data, so that the search cost is significantly reduced without performance degradation. Specifically, we observe that locating network attribution correctly is general ability for accurate visual analysis across different data distribution. Therefore, despite of pursuing higher model accuracy and complexity, we preserve attribution rank consistency between the quantized models and their full-precision counterparts via efficient capacity-aware attribution imitation for generalizable mixed-precision quantization strategy search. Extensive experiments show that our method obtains competitive accuracy-complexity trade-off compared with the state-of-the-art mixed-precision networks in significantly reduced search cost. The code is available at https://github.com/ZiweiWangTHU/GMPQ.git.","url_abs":"https://arxiv.org/abs/2108.02720v1","url_pdf":"https://arxiv.org/pdf/2108.02720v1.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":"generalizable-mixed-precision-quantization","repo_url":"https://github.com/ZiweiWangTHU/GMPQ","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.02720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02720"}},"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":"deterministic:regex_extraction","url":"https://github.com/ZiweiWangTHU/GMPQ","reach":null}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"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":"6c543b08a51e1807","entry":"MixActivConv2d","repo":"ZiweiWangTHU/GMPQ","repo_kind":"official","path":"models/quant_module.py","file_url":"https://github.com/ZiweiWangTHU/GMPQ/blob/HEAD/models/quant_module.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":"6c543b08a51e1807"}},{"code_sha256_prefix":"38ac64e2ffccc79f","entry":"MixQuantActiv","repo":"ZiweiWangTHU/GMPQ","repo_kind":"official","path":"models/quant_module.py","file_url":"https://github.com/ZiweiWangTHU/GMPQ/blob/HEAD/models/quant_module.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":"38ac64e2ffccc79f"}},{"code_sha256_prefix":"32a3a373a61f1896","entry":"MixQuantConv2d","repo":"ZiweiWangTHU/GMPQ","repo_kind":"official","path":"models/quant_module.py","file_url":"https://github.com/ZiweiWangTHU/GMPQ/blob/HEAD/models/quant_module.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":"32a3a373a61f1896"}},{"code_sha256_prefix":"6e5ee002fef7d9bc","entry":"QModule","repo":"ZiweiWangTHU/GMPQ","repo_kind":"official","path":"models/quant_module.py","file_url":"https://github.com/ZiweiWangTHU/GMPQ/blob/HEAD/models/quant_module.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":"6e5ee002fef7d9bc"}},{"code_sha256_prefix":"83c4b6d54fdedef0","entry":"QuantActiv","repo":"ZiweiWangTHU/GMPQ","repo_kind":"official","path":"models/quant_module.py","file_url":"https://github.com/ZiweiWangTHU/GMPQ/blob/HEAD/models/quant_module.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":"83c4b6d54fdedef0"}},{"code_sha256_prefix":"a780e836b4430895","entry":"QuantConv","repo":"ZiweiWangTHU/GMPQ","repo_kind":"official","path":"models/quant_module.py","file_url":"https://github.com/ZiweiWangTHU/GMPQ/blob/HEAD/models/quant_module.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":"a780e836b4430895"}},{"code_sha256_prefix":"0576ea76dd26fcd6","entry":"STE","repo":"ZiweiWangTHU/GMPQ","repo_kind":"official","path":"models/quant_module.py","file_url":"https://github.com/ZiweiWangTHU/GMPQ/blob/HEAD/models/quant_module.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":"0576ea76dd26fcd6"}},{"code_sha256_prefix":"ee2ba6d38e71a370","entry":"SharedMixQuantConv2d","repo":"ZiweiWangTHU/GMPQ","repo_kind":"official","path":"models/quant_module.py","file_url":"https://github.com/ZiweiWangTHU/GMPQ/blob/HEAD/models/quant_module.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":"ee2ba6d38e71a370"}},{"code_sha256_prefix":"8d472ac9cdab47d3","entry":"calibrate","repo":"ZiweiWangTHU/GMPQ","repo_kind":"official","path":"models/quant_module.py","file_url":"https://github.com/ZiweiWangTHU/GMPQ/blob/HEAD/models/quant_module.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":"8d472ac9cdab47d3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}