{"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/eq-net-elastic-quantization-neural-networks","title":"EQ-Net: Elastic Quantization Neural Networks","arxiv_id":"2308.07650","date":"2023-08-15","proceeding":"ICCV 2023 1","authors":["Ke Xu","Lei Han","Ye Tian","Shangshang Yang","Xingyi Zhang"],"abstract":"Current model quantization methods have shown their promising capability in reducing storage space and computation complexity. However, due to the diversity of quantization forms supported by different hardware, one limitation of existing solutions is that usually require repeated optimization for different scenarios. How to construct a model with flexible quantization forms has been less studied. In this paper, we explore a one-shot network quantization regime, named Elastic Quantization Neural Networks (EQ-Net), which aims to train a robust weight-sharing quantization supernet. First of all, we propose an elastic quantization space (including elastic bit-width, granularity, and symmetry) to adapt to various mainstream quantitative forms. Secondly, we propose the Weight Distribution Regularization Loss (WDR-Loss) and Group Progressive Guidance Loss (GPG-Loss) to bridge the inconsistency of the distribution for weights and output logits in the elastic quantization space gap. Lastly, we incorporate genetic algorithms and the proposed Conditional Quantization-Aware Accuracy Predictor (CQAP) as an estimator to quickly search mixed-precision quantized neural networks in supernet. Extensive experiments demonstrate that our EQ-Net is close to or even better than its static counterparts as well as state-of-the-art robust bit-width methods. Code can be available at \\href{https://github.com/xuke225/EQ-Net.git}{https://github.com/xuke225/EQ-Net}.","url_abs":"https://arxiv.org/abs/2308.07650v1","url_pdf":"https://arxiv.org/pdf/2308.07650v1.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":"eq-net-elastic-quantization-neural-networks","repo_url":"https://github.com/xuke225/eq-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.07650","atlas_url":"https://app.syntology.ai/?focus=2308.07650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07650"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/xuke225/EQ-Net","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":5,"ran_fixture":1},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":7,"samples":[{"code_sha256_prefix":"675da8641c602b03","entry":"round_ste","repo":"xuke225/EQ-Net","repo_kind":"official","path":"module/base_lsq.py","file_url":"https://github.com/xuke225/EQ-Net/blob/HEAD/module/base_lsq.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"675da8641c602b03"}},{"code_sha256_prefix":"f287df11a2dad0bc","entry":"grad_scale","repo":"xuke225/EQ-Net","repo_kind":"official","path":"module/base_lsq.py","file_url":"https://github.com/xuke225/EQ-Net/blob/HEAD/module/base_lsq.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":"f287df11a2dad0bc"}},{"code_sha256_prefix":"bc1bf5bb29e60206","entry":"is_absorbing","repo":"xuke225/EQ-Net","repo_kind":"official","path":"module/merge_bn.py","file_url":"https://github.com/xuke225/EQ-Net/blob/HEAD/module/merge_bn.py","link_basis":"harvester_set","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":"bc1bf5bb29e60206"}},{"code_sha256_prefix":"06ddc213753098ff","entry":"is_bn","repo":"xuke225/EQ-Net","repo_kind":"official","path":"module/merge_bn.py","file_url":"https://github.com/xuke225/EQ-Net/blob/HEAD/module/merge_bn.py","link_basis":"harvester_set","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":"06ddc213753098ff"}},{"code_sha256_prefix":"08c6ea7576220a13","entry":"lp_loss","repo":"xuke225/EQ-Net","repo_kind":"official","path":"module/base_uaq.py","file_url":"https://github.com/xuke225/EQ-Net/blob/HEAD/module/base_uaq.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"08c6ea7576220a13"}},{"code_sha256_prefix":"dc5d39ef0041492d","entry":"lp_loss","repo":"xuke225/EQ-Net","repo_kind":"official","path":"module/base_lsq.py","file_url":"https://github.com/xuke225/EQ-Net/blob/HEAD/module/base_lsq.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":"dc5d39ef0041492d"}},{"code_sha256_prefix":"01bcbe5e5968a480","entry":"search_merge_and_remove_bn","repo":"xuke225/EQ-Net","repo_kind":"official","path":"module/merge_bn.py","file_url":"https://github.com/xuke225/EQ-Net/blob/HEAD/module/merge_bn.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":"01bcbe5e5968a480"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}