{"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/uniformer-unifying-convolution-and-self","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","arxiv_id":"2201.09450","date":"2022-01-24","proceeding":null,"authors":["Kunchang Li","Yali Wang","Junhao Zhang","Peng Gao","Guanglu Song","Yu Liu","Hongsheng Li","Yu Qiao"],"abstract":"It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have been two dominant frameworks in the past few years. Though CNNs can efficiently decrease local redundancy by convolution within a small neighborhood, the limited receptive field makes it hard to capture global dependency. Alternatively, ViTs can effectively capture long-range dependency via self-attention, while blind similarity comparisons among all the tokens lead to high redundancy. To resolve these problems, we propose a novel Unified transFormer (UniFormer), which can seamlessly integrate the merits of convolution and self-attention in a concise transformer format. Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing to tackle both redundancy and dependency for efficient and effective representation learning. Finally, we flexibly stack our UniFormer blocks into a new powerful backbone, and adopt it for various vision tasks from image to video domain, from classification to dense prediction. Without any extra training data, our UniFormer achieves 86.3 top-1 accuracy on ImageNet-1K classification. With only ImageNet-1K pre-training, it can simply achieve state-of-the-art performance in a broad range of downstream tasks, e.g., it obtains 82.9/84.8 top-1 accuracy on Kinetics-400/600, 60.9/71.2 top-1 accuracy on Sth-Sth V1/V2 video classification, 53.8 box AP and 46.4 mask AP on COCO object detection, 50.8 mIoU on ADE20K semantic segmentation, and 77.4 AP on COCO pose estimation. We further build an efficient UniFormer with 2-4x higher throughput. Code is available at https://github.com/Sense-X/UniFormer.","url_abs":"https://arxiv.org/abs/2201.09450v3","url_pdf":"https://arxiv.org/pdf/2201.09450v3.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":"uniformer-unifying-convolution-and-self","repo_url":"https://github.com/sense-x/uniformer","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"uniformer-unifying-convolution-and-self","repo_url":"https://github.com/Westlake-AI/openmixup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"uniformer-unifying-convolution-and-self","repo_url":"https://github.com/bespontaneous/ffn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"uniformer-unifying-convolution-and-self","repo_url":"https://github.com/bespontaneous/mca-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"uniformer-unifying-convolution-and-self","repo_url":"https://github.com/sithu31296/semantic-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"uniformer-unifying-convolution-and-self","repo_url":"https://github.com/Asthestarsfalll/UniFormer-MegEngine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"uniformer-unifying-convolution-and-self","repo_url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/uniformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"uniformer-unifying-convolution-and-self","repo_url":"https://gitlab.com/birder/birder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"UniFormer-L (384 res)","rank_in_archive_order":160,"of":1060,"metrics":{"GFLOPs":"39.2","Number of params":"100M","Top 1 Accuracy":"86.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"UniFormer-L","rank_in_archive_order":216,"of":1060,"metrics":{"GFLOPs":"12.6","Number of params":"100M","Top 1 Accuracy":"85.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"UniFormer-S","rank_in_archive_order":427,"of":1060,"metrics":{"GFLOPs":"3.6","Number of params":"22M","Top 1 Accuracy":"83.4%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2201.09450","atlas_url":"https://app.syntology.ai/?focus=2201.09450","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":"2201.09450"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2201.09450\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2201.09450"},"call":"get_concepts_for_paper(arxiv_id=\"2201.09450\")"}],"by_repo":[{"repo":"sense-x/uniformer","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2201.04676"],"harvested_for_calls":[{"arxiv_id":"2201.04676","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2201.04676"},"call":"get_harvested_code_for_paper(arxiv_id=\"2201.04676\")"}]},{"repo":"Westlake-AI/openmixup","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1710.09412","1712.09913","1905.04899","2312.11954"],"harvested_for_calls":[{"arxiv_id":"1710.09412","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.09412"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.09412\")"},{"arxiv_id":"1712.09913","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1712.09913"},"call":"get_harvested_code_for_paper(arxiv_id=\"1712.09913\")"},{"arxiv_id":"1905.04899","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1905.04899"},"call":"get_harvested_code_for_paper(arxiv_id=\"1905.04899\")"},{"arxiv_id":"2312.11954","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.11954"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.11954\")"}]},{"repo":"bespontaneous/ffn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2303.14817"],"harvested_for_calls":[{"arxiv_id":"2303.14817","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.14817"},"call":"get_harvested_code_for_paper(arxiv_id=\"2303.14817\")"}]},{"repo":"bespontaneous/mca-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1811.08383"],"harvested_for_calls":[{"arxiv_id":"1811.08383","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1811.08383"},"call":"get_harvested_code_for_paper(arxiv_id=\"1811.08383\")"}]},{"repo":"sithu31296/semantic-segmentation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["2105.15203","2108.07058","2201.03545"],"harvested_for_calls":[{"arxiv_id":"2105.15203","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.15203"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.15203\")"},{"arxiv_id":"2108.07058","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2108.07058"},"call":"get_harvested_code_for_paper(arxiv_id=\"2108.07058\")"},{"arxiv_id":"2201.03545","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2201.03545"},"call":"get_harvested_code_for_paper(arxiv_id=\"2201.03545\")"}]},{"repo":"Asthestarsfalll/UniFormer-MegEngine","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"leondgarse/keras_cv_attention_models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2307.09283"],"harvested_for_calls":[{"arxiv_id":"2307.09283","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2307.09283"},"call":"get_harvested_code_for_paper(arxiv_id=\"2307.09283\")"}]},{"repo":"gitlab.com/birder/birder","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"98a19e257dd95618e03e608a70bcb49223514f104adaa2efccb765f5bfc1e840","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}