{"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/transnas-bench-101-improving-transferability","title":"TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search","arxiv_id":"2105.11871","date":"2021-05-25","proceeding":"CVPR 2021 1","authors":["Yawen Duan","Xin Chen","Hang Xu","Zewei Chen","Xiaodan Liang","Tong Zhang","Zhenguo Li"],"abstract":"Recent breakthroughs of Neural Architecture Search (NAS) extend the field's research scope towards a broader range of vision tasks and more diversified search spaces. While existing NAS methods mostly design architectures on a single task, algorithms that look beyond single-task search are surging to pursue a more efficient and universal solution across various tasks. Many of them leverage transfer learning and seek to preserve, reuse, and refine network design knowledge to achieve higher efficiency in future tasks. However, the enormous computational cost and experiment complexity of cross-task NAS are imposing barriers for valuable research in this direction. Existing NAS benchmarks all focus on one type of vision task, i.e., classification. In this work, we propose TransNAS-Bench-101, a benchmark dataset containing network performance across seven tasks, covering classification, regression, pixel-level prediction, and self-supervised tasks. This diversity provides opportunities to transfer NAS methods among tasks and allows for more complex transfer schemes to evolve. We explore two fundamentally different types of search space: cell-level search space and macro-level search space. With 7,352 backbones evaluated on seven tasks, 51,464 trained models with detailed training information are provided. With TransNAS-Bench-101, we hope to encourage the advent of exceptional NAS algorithms that raise cross-task search efficiency and generalizability to the next level. Our dataset file will be available at Mindspore, VEGA.","url_abs":"https://arxiv.org/abs/2105.11871v1","url_pdf":"https://arxiv.org/pdf/2105.11871v1.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":"transnas-bench-101-improving-transferability","repo_url":"https://github.com/Edge-AI-Acceleration-Lab/RBFleX-NAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"transnas-bench-101-improving-transferability","repo_url":"https://github.com/kmdanielduan/TransNASBench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"transnas-bench-101-improving-transferability","repo_url":"https://github.com/tomomasayamasaki/RBFleX-NAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"transnas-bench-101-improving-transferability","repo_url":"https://github.com/yawen-d/transnasbench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"vega","method_name":"VEGA"}],"datasets_introduced":[{"slug":"transnas-bench-101","name":"TransNAS-Bench-101","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.11871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11871"}},"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/tomomasayamasaki/RBFleX-NAS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yawen-d/transnasbench","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Edge-AI-Acceleration-Lab/RBFleX-NAS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kmdanielduan/TransNASBench","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"listed":{"samples":9,"ran":0,"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":"e6683d2088f920e6","entry":"classification","repo":"kmdanielduan/TransNASBench","repo_kind":"listed","path":"lib/procedures/task_vis.py","file_url":"https://github.com/kmdanielduan/TransNASBench/blob/HEAD/lib/procedures/task_vis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e6683d2088f920e6"}},{"code_sha256_prefix":"5842dd066c74c704","entry":"get_confusion_matrix","repo":"kmdanielduan/TransNASBench","repo_kind":"listed","path":"lib/models/utils.py","file_url":"https://github.com/kmdanielduan/TransNASBench/blob/HEAD/lib/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5842dd066c74c704"}},{"code_sha256_prefix":"da484d75b643a432","entry":"get_flops","repo":"kmdanielduan/TransNASBench","repo_kind":"listed","path":"lib/models/model_info.py","file_url":"https://github.com/kmdanielduan/TransNASBench/blob/HEAD/lib/models/model_info.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da484d75b643a432"}},{"code_sha256_prefix":"8629889d5612c287","entry":"get_inference_time","repo":"kmdanielduan/TransNASBench","repo_kind":"listed","path":"lib/models/model_info.py","file_url":"https://github.com/kmdanielduan/TransNASBench/blob/HEAD/lib/models/model_info.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8629889d5612c287"}},{"code_sha256_prefix":"a8ddf8c8aed9b1bc","entry":"get_params","repo":"kmdanielduan/TransNASBench","repo_kind":"listed","path":"lib/models/model_info.py","file_url":"https://github.com/kmdanielduan/TransNASBench/blob/HEAD/lib/models/model_info.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8ddf8c8aed9b1bc"}},{"code_sha256_prefix":"a3a03882516092f5","entry":"get_topk_acc","repo":"kmdanielduan/TransNASBench","repo_kind":"listed","path":"lib/models/utils.py","file_url":"https://github.com/kmdanielduan/TransNASBench/blob/HEAD/lib/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3a03882516092f5"}},{"code_sha256_prefix":"f1eae5bb66aa2d1b","entry":"merge_list","repo":"kmdanielduan/TransNASBench","repo_kind":"listed","path":"lib/models/utils.py","file_url":"https://github.com/kmdanielduan/TransNASBench/blob/HEAD/lib/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1eae5bb66aa2d1b"}},{"code_sha256_prefix":"a3fc3801fa7b9bb4","entry":"set_img_color","repo":"kmdanielduan/TransNASBench","repo_kind":"listed","path":"lib/procedures/task_vis.py","file_url":"https://github.com/kmdanielduan/TransNASBench/blob/HEAD/lib/procedures/task_vis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3fc3801fa7b9bb4"}},{"code_sha256_prefix":"2ee061ffaae87c15","entry":"tensor2np_img","repo":"kmdanielduan/TransNASBench","repo_kind":"listed","path":"lib/procedures/task_vis.py","file_url":"https://github.com/kmdanielduan/TransNASBench/blob/HEAD/lib/procedures/task_vis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ee061ffaae87c15"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}