{"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/qimera-data-free-quantization-with-synthetic","title":"Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples","arxiv_id":"2111.02625","date":"2021-11-04","proceeding":"NeurIPS 2021 12","authors":["Kanghyun Choi","Deokki Hong","Noseong Park","Youngsok Kim","Jinho Lee"],"abstract":"Model quantization is known as a promising method to compress deep neural networks, especially for inferences on lightweight mobile or edge devices. However, model quantization usually requires access to the original training data to maintain the accuracy of the full-precision models, which is often infeasible in real-world scenarios for security and privacy issues. A popular approach to perform quantization without access to the original data is to use synthetically generated samples, based on batch-normalization statistics or adversarial learning. However, the drawback of such approaches is that they primarily rely on random noise input to the generator to attain diversity of the synthetic samples. We find that this is often insufficient to capture the distribution of the original data, especially around the decision boundaries. To this end, we propose Qimera, a method that uses superposed latent embeddings to generate synthetic boundary supporting samples. For the superposed embeddings to better reflect the original distribution, we also propose using an additional disentanglement mapping layer and extracting information from the full-precision model. The experimental results show that Qimera achieves state-of-the-art performances for various settings on data-free quantization. Code is available at https://github.com/iamkanghyunchoi/qimera.","url_abs":"https://arxiv.org/abs/2111.02625v1","url_pdf":"https://arxiv.org/pdf/2111.02625v1.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":"qimera-data-free-quantization-with-synthetic","repo_url":"https://github.com/iamkanghyunchoi/qimera","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qimera-data-free-quantization-with-synthetic","repo_url":"https://github.com/iamkanghyunchoi/ait","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-free-quantization","task_name":"Data Free Quantization"},{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/data-free-quantization-on-cifar-100","task":"Data Free Quantization","dataset":"CIFAR-100","model":"ResNet-20 CIFAR-100","rank_in_archive_order":1,"of":3,"metrics":{"CIFAR-100 W4A4 Top-1 Accuracy":"65.10","CIFAR-100 W5A5 Top-1 Accuracy":"69.02"},"uses_additional_data":false},{"leaderboard":"/sota/data-free-quantization-on-cifar10","task":"Data Free Quantization","dataset":"CIFAR10","model":"ResNet-20 CIFAR-10","rank_in_archive_order":1,"of":3,"metrics":{"CIFAR-10 W4A4 Top-1 Accuracy":"91.26","CIFAR-10 W5A5 Top-1 Accuracy":"93.46"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.02625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02625"}},"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/iamkanghyunchoi/qimera","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iamkanghyunchoi/ait","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"57fb6c58ad910afa","entry":"GeneratorQimera","repo":"iamkanghyunchoi/ait","repo_kind":"listed","path":"Qimera_AIT/experiments.py","file_url":"https://github.com/iamkanghyunchoi/ait/blob/HEAD/Qimera_AIT/experiments.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"57fb6c58ad910afa"}},{"code_sha256_prefix":"ed72c1f6f1ee4cc1","entry":"reduce_df","repo":"iamkanghyunchoi/qimera","repo_kind":"official","path":"experiments.py","file_url":"https://github.com/iamkanghyunchoi/qimera/blob/HEAD/experiments.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ed72c1f6f1ee4cc1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}