{"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/tf-nas-rethinking-three-search-freedoms-of","title":"TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search","arxiv_id":"2008.05314","date":"2020-08-12","proceeding":"ECCV 2020 8","authors":["Yibo Hu","Xiang Wu","Ran He"],"abstract":"With the flourish of differentiable neural architecture search (NAS), automatically searching latency-constrained architectures gives a new perspective to reduce human labor and expertise. However, the searched architectures are usually suboptimal in accuracy and may have large jitters around the target latency. In this paper, we rethink three freedoms of differentiable NAS, i.e. operation-level, depth-level and width-level, and propose a novel method, named Three-Freedom NAS (TF-NAS), to achieve both good classification accuracy and precise latency constraint. For the operation-level, we present a bi-sampling search algorithm to moderate the operation collapse. For the depth-level, we introduce a sink-connecting search space to ensure the mutual exclusion between skip and other candidate operations, as well as eliminate the architecture redundancy. For the width-level, we propose an elasticity-scaling strategy that achieves precise latency constraint in a progressively fine-grained manner. Experiments on ImageNet demonstrate the effectiveness of TF-NAS. Particularly, our searched TF-NAS-A obtains 76.9% top-1 accuracy, achieving state-of-the-art results with less latency. The total search time is only 1.8 days on 1 Titan RTX GPU. Code is available at https://github.com/AberHu/TF-NAS.","url_abs":"https://arxiv.org/abs/2008.05314v1","url_pdf":"https://arxiv.org/pdf/2008.05314v1.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":"tf-nas-rethinking-three-search-freedoms-of","repo_url":"https://github.com/AberHu/TF-NAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.05314","atlas_url":"https://app.syntology.ai/?focus=2008.05314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.05314"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/AberHu/TF-NAS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":"07283a69b20f929b","entry":"cv2_loader","repo":"AberHu/TF-NAS","repo_kind":"official","path":"dataset/dataset.py","file_url":"https://github.com/AberHu/TF-NAS/blob/HEAD/dataset/dataset.py","link_basis":"first_harvest_node","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":"07283a69b20f929b"}},{"code_sha256_prefix":"4157231d4cff92f0","entry":"default_list_reader","repo":"AberHu/TF-NAS","repo_kind":"official","path":"dataset/dataset.py","file_url":"https://github.com/AberHu/TF-NAS/blob/HEAD/dataset/dataset.py","link_basis":"first_harvest_node","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":"4157231d4cff92f0"}},{"code_sha256_prefix":"ef31a5ef33edb8ff","entry":"get_mc_num_dddict","repo":"AberHu/TF-NAS","repo_kind":"official","path":"parsing_model.py","file_url":"https://github.com/AberHu/TF-NAS/blob/HEAD/parsing_model.py","link_basis":"first_harvest_node","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":"ef31a5ef33edb8ff"}},{"code_sha256_prefix":"4f6431f21fad8ee4","entry":"get_op_and_depth_weights","repo":"AberHu/TF-NAS","repo_kind":"official","path":"parsing_model.py","file_url":"https://github.com/AberHu/TF-NAS/blob/HEAD/parsing_model.py","link_basis":"first_harvest_node","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":"4f6431f21fad8ee4"}},{"code_sha256_prefix":"c31407c1275921c3","entry":"parse_architecture","repo":"AberHu/TF-NAS","repo_kind":"official","path":"parsing_model.py","file_url":"https://github.com/AberHu/TF-NAS/blob/HEAD/parsing_model.py","link_basis":"first_harvest_node","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":"c31407c1275921c3"}},{"code_sha256_prefix":"5b64a4093002f637","entry":"pil_loader","repo":"AberHu/TF-NAS","repo_kind":"official","path":"dataset/dataset.py","file_url":"https://github.com/AberHu/TF-NAS/blob/HEAD/dataset/dataset.py","link_basis":"first_harvest_node","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":"5b64a4093002f637"}},{"code_sha256_prefix":"91cd803b76cc8823","entry":"reduce_tensor","repo":"AberHu/TF-NAS","repo_kind":"official","path":"train_eval_amp.py","file_url":"https://github.com/AberHu/TF-NAS/blob/HEAD/train_eval_amp.py","link_basis":"first_harvest_node","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":"91cd803b76cc8823"}},{"code_sha256_prefix":"60f6c877e2ea4c5b","entry":"set_layer_from_config","repo":"AberHu/TF-NAS","repo_kind":"official","path":"models/layers.py","file_url":"https://github.com/AberHu/TF-NAS/blob/HEAD/models/layers.py","link_basis":"first_harvest_node","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":"60f6c877e2ea4c5b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}