{"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/nsganetv2-evolutionary-multi-objective","title":"NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search","arxiv_id":"2007.10396","date":"2020-07-20","proceeding":"ECCV 2020 8","authors":["Zhichao Lu","Kalyanmoy Deb","Erik Goodman","Wolfgang Banzhaf","Vishnu Naresh Boddeti"],"abstract":"In this paper, we propose an efficient NAS algorithm for generating task-specific models that are competitive under multiple competing objectives. It comprises of two surrogates, one at the architecture level to improve sample efficiency and one at the weights level, through a supernet, to improve gradient descent training efficiency. On standard benchmark datasets (C10, C100, ImageNet), the resulting models, dubbed NSGANetV2, either match or outperform models from existing approaches with the search being orders of magnitude more sample efficient. Furthermore, we demonstrate the effectiveness and versatility of the proposed method on six diverse non-standard datasets, e.g. STL-10, Flowers102, Oxford Pets, FGVC Aircrafts etc. In all cases, NSGANetV2s improve the state-of-the-art (under mobile setting), suggesting that NAS can be a viable alternative to conventional transfer learning approaches in handling diverse scenarios such as small-scale or fine-grained datasets. Code is available at https://github.com/mikelzc1990/nsganetv2","url_abs":"https://arxiv.org/abs/2007.10396v1","url_pdf":"https://arxiv.org/pdf/2007.10396v1.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":"nsganetv2-evolutionary-multi-objective","repo_url":"https://github.com/mikelzc1990/nsganetv2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"neural-architecture-search","method_name":"Neural Architecture Search"},{"method_slug":"ppo","method_name":"PPO"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"NSGANetV2","rank_in_archive_order":31,"of":117,"metrics":{"Percentage correct":"92.0"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"NSGANetV2-xl","rank_in_archive_order":17,"of":135,"metrics":{"Accuracy":"80.4","MACs":"593M","Params":"8.7M","Top-1 Error Rate":"19.6"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"NSGANetV2-l","rank_in_archive_order":35,"of":135,"metrics":{"Accuracy":"79.1","MACs":"400M","Params":"8.0M","Top-1 Error Rate":"20.9"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"NSGANetV2-m","rank_in_archive_order":49,"of":135,"metrics":{"Accuracy":"78.3","MACs":"312M","Params":"7.7M","Top-1 Error Rate":"21.7"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"NSGANetV2-s","rank_in_archive_order":64,"of":135,"metrics":{"Accuracy":"77.4","MACs":"225M","Params":"6.1M","Top-1 Error Rate":"22.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.10396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10396"}},"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/mikelzc1990/nsganetv2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"unverified":6},"by_repo_kind":{"official":{"samples":8,"ran":2,"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":"6db40799d999d837","entry":"pad_none","repo":"mikelzc1990/nsganetv2","repo_kind":"official","path":"evaluator.py","file_url":"https://github.com/mikelzc1990/nsganetv2/blob/HEAD/evaluator.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6db40799d999d837"}},{"code_sha256_prefix":"59ef743ae49b58e1","entry":"parse_string_list","repo":"mikelzc1990/nsganetv2","repo_kind":"official","path":"evaluator.py","file_url":"https://github.com/mikelzc1990/nsganetv2/blob/HEAD/evaluator.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59ef743ae49b58e1"}},{"code_sha256_prefix":"ede09871c3c8b79b","entry":"get_acc_predictor","repo":"mikelzc1990/nsganetv2","repo_kind":"official","path":"acc_predictor/factory.py","file_url":"https://github.com/mikelzc1990/nsganetv2/blob/HEAD/acc_predictor/factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ede09871c3c8b79b"}},{"code_sha256_prefix":"285dcbbdea2ec2b3","entry":"get_correlation","repo":"mikelzc1990/nsganetv2","repo_kind":"official","path":"utils.py","file_url":"https://github.com/mikelzc1990/nsganetv2/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"285dcbbdea2ec2b3"}},{"code_sha256_prefix":"2d6dc16493521afd","entry":"infer","repo":"mikelzc1990/nsganetv2","repo_kind":"official","path":"train_cifar.py","file_url":"https://github.com/mikelzc1990/nsganetv2/blob/HEAD/train_cifar.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d6dc16493521afd"}},{"code_sha256_prefix":"90e3cacca1501e59","entry":"look_up_latency","repo":"mikelzc1990/nsganetv2","repo_kind":"official","path":"utils.py","file_url":"https://github.com/mikelzc1990/nsganetv2/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90e3cacca1501e59"}},{"code_sha256_prefix":"22ac9a49daa933c8","entry":"train","repo":"mikelzc1990/nsganetv2","repo_kind":"official","path":"train_cifar.py","file_url":"https://github.com/mikelzc1990/nsganetv2/blob/HEAD/train_cifar.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"22ac9a49daa933c8"}},{"code_sha256_prefix":"b5886490f0a3569d","entry":"validate","repo":"mikelzc1990/nsganetv2","repo_kind":"official","path":"train_imagenet.py","file_url":"https://github.com/mikelzc1990/nsganetv2/blob/HEAD/train_imagenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b5886490f0a3569d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}