{"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/evolving-search-space-for-neural-architecture","title":"Evolving Search Space for Neural Architecture Search","arxiv_id":"2011.10904","date":"2020-11-22","proceeding":"ICCV 2021 10","authors":["Yuanzheng Ci","Chen Lin","Ming Sun","BoYu Chen","Hongwen Zhang","Wanli Ouyang"],"abstract":"The automation of neural architecture design has been a coveted alternative to human experts. Recent works have small search space, which is easier to optimize but has a limited upper bound of the optimal solution. Extra human design is needed for those methods to propose a more suitable space with respect to the specific task and algorithm capacity. To further enhance the degree of automation for neural architecture search, we present a Neural Search-space Evolution (NSE) scheme that iteratively amplifies the results from the previous effort by maintaining an optimized search space subset. This design minimizes the necessity of a well-designed search space. We further extend the flexibility of obtainable architectures by introducing a learnable multi-branch setting. By employing the proposed method, a consistent performance gain is achieved during a progressive search over upcoming search spaces. We achieve 77.3% top-1 retrain accuracy on ImageNet with 333M FLOPs, which yielded a state-of-the-art performance among previous auto-generated architectures that do not involve knowledge distillation or weight pruning. When the latency constraint is adopted, our result also performs better than the previous best-performing mobile models with a 77.9% Top-1 retrain accuracy.","url_abs":"https://arxiv.org/abs/2011.10904v2","url_pdf":"https://arxiv.org/pdf/2011.10904v2.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":"evolving-search-space-for-neural-architecture","repo_url":"https://github.com/orashi/NSE_NAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.10904","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}