{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/autoformer-searching-transformers-for-visual","title":"AutoFormer: Searching Transformers for Visual Recognition","arxiv_id":"2107.00651","date":"2021-07-01","proceeding":"ICCV 2021 10","authors":["Minghao Chen","Houwen Peng","Jianlong Fu","Haibin Ling"],"abstract":"Recently, pure transformer-based models have shown great potentials for vision tasks such as image classification and detection. However, the design of transformer networks is challenging. It has been observed that the depth, embedding dimension, and number of heads can largely affect the performance of vision transformers. Previous models configure these dimensions based upon manual crafting. In this work, we propose a new one-shot architecture search framework, namely AutoFormer, dedicated to vision transformer search. AutoFormer entangles the weights of different blocks in the same layers during supernet training. Benefiting from the strategy, the trained supernet allows thousands of subnets to be very well-trained. Specifically, the performance of these subnets with weights inherited from the supernet is comparable to those retrained from scratch. Besides, the searched models, which we refer to AutoFormers, surpass the recent state-of-the-arts such as ViT and DeiT. In particular, AutoFormer-tiny/small/base achieve 74.7%/81.7%/82.4% top-1 accuracy on ImageNet with 5.7M/22.9M/53.7M parameters, respectively. Lastly, we verify the transferability of AutoFormer by providing the performance on downstream benchmarks and distillation experiments. Code and models are available at https://github.com/microsoft/AutoML.","url_abs":"https://arxiv.org/abs/2107.00651v1","url_pdf":"https://arxiv.org/pdf/2107.00651v1.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":"autoformer-searching-transformers-for-visual","repo_url":"https://github.com/microsoft/AutoML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"autoformer-searching-transformers-for-visual","repo_url":"https://github.com/microsoft/cream","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"deit","method_name":"DeiT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-oxford","task":"Fine-Grained Image Classification","dataset":"Oxford 102 Flowers","model":"AutoFormer-S | 384","rank_in_archive_order":23,"of":25,"metrics":{"Top 1 Accuracy":"98.8"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford-1","task":"Fine-Grained Image Classification","dataset":"Oxford-IIIT Pet Dataset","model":"AutoFormer-S | 384","rank_in_archive_order":10,"of":15,"metrics":{"Accuracy":"94.9%"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","task":"Fine-Grained Image Classification","dataset":"Stanford Cars","model":"AutoFormer-S | 384","rank_in_archive_order":63,"of":83,"metrics":{"Accuracy":"93.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"AutoFormer-S | 384","rank_in_archive_order":18,"of":265,"metrics":{"Percentage correct":"99.1"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"AutoFormer-base","rank_in_archive_order":539,"of":1060,"metrics":{"GFLOPs":"11","Number of params":"54M","Top 1 Accuracy":"82.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"AutoFormer-small","rank_in_archive_order":617,"of":1060,"metrics":{"GFLOPs":"5.1","Number of params":"22.9M","Top 1 Accuracy":"81.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"AutoFormer-tiny","rank_in_archive_order":971,"of":1060,"metrics":{"GFLOPs":"1.3","Number of params":"5.7M","Top 1 Accuracy":"74.7%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.00651","atlas_url":"https://app.syntology.ai/?focus=2107.00651","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2107.00651"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2107.00651\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2107.00651"},"call":"get_concepts_for_paper(arxiv_id=\"2107.00651\")"}],"by_repo":[{"repo":"microsoft/AutoML","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2204.07154"],"harvested_for_calls":[{"arxiv_id":"2204.07154","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2204.07154"},"call":"get_harvested_code_for_paper(arxiv_id=\"2204.07154\")"}]},{"repo":"microsoft/cream","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["2107.14222","2207.10666","2305.07027","2309.12314"],"harvested_for_calls":[{"arxiv_id":"2107.14222","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2107.14222"},"call":"get_harvested_code_for_paper(arxiv_id=\"2107.14222\")"},{"arxiv_id":"2207.10666","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2207.10666"},"call":"get_harvested_code_for_paper(arxiv_id=\"2207.10666\")"},{"arxiv_id":"2305.07027","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.07027"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.07027\")"},{"arxiv_id":"2309.12314","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.12314"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.12314\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"af1b6147a0537f6704b273592e80ab40baab8953ea1f4000d8f64f8b6ef734d4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}