{"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/auto-prox-training-free-vision-transformer","title":"Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery","arxiv_id":"2312.09059","date":"2023-12-14","proceeding":null,"authors":["Zimian Wei","Lujun Li","Peijie Dong","Zheng Hui","Anggeng Li","Menglong Lu","Hengyue Pan","Zhiliang Tian","Dongsheng Li"],"abstract":"The substantial success of Vision Transformer (ViT) in computer vision tasks is largely attributed to the architecture design. This underscores the necessity of efficient architecture search for designing better ViTs automatically. As training-based architecture search methods are computationally intensive, there is a growing interest in training-free methods that use zero-cost proxies to score ViTs. However, existing training-free approaches require expert knowledge to manually design specific zero-cost proxies. Moreover, these zero-cost proxies exhibit limitations to generalize across diverse domains. In this paper, we introduce Auto-Prox, an automatic proxy discovery framework, to address the problem. First, we build the ViT-Bench-101, which involves different ViT candidates and their actual performance on multiple datasets. Utilizing ViT-Bench-101, we can evaluate zero-cost proxies based on their score-accuracy correlation. Then, we represent zero-cost proxies with computation graphs and organize the zero-cost proxy search space with ViT statistics and primitive operations. To discover generic zero-cost proxies, we propose a joint correlation metric to evolve and mutate different zero-cost proxy candidates. We introduce an elitism-preserve strategy for search efficiency to achieve a better trade-off between exploitation and exploration. Based on the discovered zero-cost proxy, we conduct a ViT architecture search in a training-free manner. Extensive experiments demonstrate that our method generalizes well to different datasets and achieves state-of-the-art results both in ranking correlation and final accuracy. Codes can be found at https://github.com/lilujunai/Auto-Prox-AAAI24.","url_abs":"https://arxiv.org/abs/2312.09059v1","url_pdf":"https://arxiv.org/pdf/2312.09059v1.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":"auto-prox-training-free-vision-transformer","repo_url":"https://github.com/lilujunai/auto-prox-aaai24","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.09059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09059"}},"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/lilujunai/auto-prox-aaai24","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":2,"ran_draft_wrong":2,"ran":1},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"72a860a9aff50105","entry":"calc_dropout","repo":"lilujunai/auto-prox-aaai24","repo_kind":"official","path":"pycls/models/auto/autoformer_supernet.py","file_url":"https://github.com/lilujunai/auto-prox-aaai24/blob/HEAD/pycls/models/auto/autoformer_supernet.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"72a860a9aff50105"}},{"code_sha256_prefix":"08a5be1ffa0676e3","entry":"gelu","repo":"lilujunai/auto-prox-aaai24","repo_kind":"official","path":"pycls/models/auto/autoformer_subnet.py","file_url":"https://github.com/lilujunai/auto-prox-aaai24/blob/HEAD/pycls/models/auto/autoformer_subnet.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"08a5be1ffa0676e3"}},{"code_sha256_prefix":"963bc33b77cf8148","entry":"sample_bias","repo":"lilujunai/auto-prox-aaai24","repo_kind":"official","path":"pycls/models/auto/module/Linear_super.py","file_url":"https://github.com/lilujunai/auto-prox-aaai24/blob/HEAD/pycls/models/auto/module/Linear_super.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"963bc33b77cf8148"}},{"code_sha256_prefix":"1d3488a4b38ea75d","entry":"sample_weight","repo":"lilujunai/auto-prox-aaai24","repo_kind":"official","path":"pycls/models/auto/module/Linear_super.py","file_url":"https://github.com/lilujunai/auto-prox-aaai24/blob/HEAD/pycls/models/auto/module/Linear_super.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d3488a4b38ea75d"}},{"code_sha256_prefix":"fb5908c47c2af90c","entry":"softmax","repo":"lilujunai/auto-prox-aaai24","repo_kind":"official","path":"pycls/models/auto/module/multihead_super.py","file_url":"https://github.com/lilujunai/auto-prox-aaai24/blob/HEAD/pycls/models/auto/module/multihead_super.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb5908c47c2af90c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}