{"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/du-darts-decreasing-the-uncertainty-of","title":"DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture Search","arxiv_id":null,"date":"2021-11-23","proceeding":"BMVC 2021 11","authors":["Shun Lu","Yu Hu","Longxing Yang","Zihao Sun","Jilin Mei","Yiming Zeng","Xiaowei Li"],"abstract":"Differentiable Neural Architecture Search (DARTS) recently attracts a lot of research attention because of its high efficiency. However, the competition of candidate operations in DARTS introduces high uncertainty for selecting the truly important operation, thus leading to serious performance collapse. In this work, we decrease the uncertainty of differentiable architecture search (DU-DARTS) by enforcing the distribution of architecture parameters to approach the one-hot categorical distribution and by replacing the zero operation with a gate switch. Without any extra search cost, our method achieves state-of-the-art performance with 2.32%, 16.74%, and 24.1% test error on CIFAR-10, CIFAR-100, and ImageNet datasets, respectively. Moreover, DU-DARTS can robustly find an excellent architecture on NAS-Bench-1Shot1 and NAS-Bench-201, which further demonstrates the effectiveness of our method. The source code is available at https://github.com/ShunLu91/DU-DARTS.","url_abs":"https://www.bmvc2021-virtualconference.com/conference/papers/paper_0209.html","url_pdf":"https://www.bmvc2021-virtualconference.com/assets/papers/0209.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":"du-darts-decreasing-the-uncertainty-of","repo_url":"https://github.com/ShunLu91/DU-DARTS","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"darts","method_name":"DARTS"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","task":"Neural Architecture Search","dataset":"CIFAR-10","model":"DU-DARTS","rank_in_archive_order":11,"of":41,"metrics":{"Parameters":"3.8M","Search Time (GPU days)":"0.4","Top-1 Error Rate":"2.32%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-cifar-100-1","task":"Neural Architecture Search","dataset":"CIFAR-100","model":"DU-DARTS","rank_in_archive_order":9,"of":13,"metrics":{"PARAMS":"3.1M","Percentage Error":" 16.74"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"DU-DARTS","rank_in_archive_order":100,"of":135,"metrics":{"Accuracy":"75.9","Params":"5.3M","Top-1 Error Rate":"24.1"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-1","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-10","model":"DU-DARTS","rank_in_archive_order":20,"of":37,"metrics":{"Accuracy (Test)":" 93.86","Accuracy (Val)":"91.21"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-2","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-100","model":"DU-DARTS","rank_in_archive_order":20,"of":40,"metrics":{"Accuracy (Test)":"71.84","Accuracy (Val)":"71.88"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201","task":"Neural Architecture Search","dataset":"NAS-Bench-201, ImageNet-16-120","model":"DU-DARTS","rank_in_archive_order":22,"of":49,"metrics":{"Accuracy (Test)":"45.94"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}