{"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/metaformer-baselines-for-vision","title":"MetaFormer Baselines for Vision","arxiv_id":"2210.13452","date":"2022-10-24","proceeding":null,"authors":["Weihao Yu","Chenyang Si","Pan Zhou","Mi Luo","Yichen Zhou","Jiashi Feng","Shuicheng Yan","Xinchao Wang"],"abstract":"MetaFormer, the abstracted architecture of Transformer, has been found to play a significant role in achieving competitive performance. In this paper, we further explore the capacity of MetaFormer, again, without focusing on token mixer design: we introduce several baseline models under MetaFormer using the most basic or common mixers, and summarize our observations as follows: (1) MetaFormer ensures solid lower bound of performance. By merely adopting identity mapping as the token mixer, the MetaFormer model, termed IdentityFormer, achieves >80% accuracy on ImageNet-1K. (2) MetaFormer works well with arbitrary token mixers. When specifying the token mixer as even a random matrix to mix tokens, the resulting model RandFormer yields an accuracy of >81%, outperforming IdentityFormer. Rest assured of MetaFormer's results when new token mixers are adopted. (3) MetaFormer effortlessly offers state-of-the-art results. With just conventional token mixers dated back five years ago, the models instantiated from MetaFormer already beat state of the art. (a) ConvFormer outperforms ConvNeXt. Taking the common depthwise separable convolutions as the token mixer, the model termed ConvFormer, which can be regarded as pure CNNs, outperforms the strong CNN model ConvNeXt. (b) CAFormer sets new record on ImageNet-1K. By simply applying depthwise separable convolutions as token mixer in the bottom stages and vanilla self-attention in the top stages, the resulting model CAFormer sets a new record on ImageNet-1K: it achieves an accuracy of 85.5% at 224x224 resolution, under normal supervised training without external data or distillation. In our expedition to probe MetaFormer, we also find that a new activation, StarReLU, reduces 71% FLOPs of activation compared with GELU yet achieves better performance. We expect StarReLU to find great potential in MetaFormer-like models alongside other neural networks.","url_abs":"https://arxiv.org/abs/2210.13452v4","url_pdf":"https://arxiv.org/pdf/2210.13452v4.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":"metaformer-baselines-for-vision","repo_url":"https://github.com/rwightman/pytorch-image-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"metaformer-baselines-for-vision","repo_url":"https://github.com/sail-sg/metaformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"metaformer-baselines-for-vision","repo_url":"https://github.com/Westlake-AI/MogaNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"metaformer-baselines-for-vision","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":"metaformer-baselines-for-vision","repo_url":"https://github.com/sail-sg/poolformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"metaformer-baselines-for-vision","repo_url":"https://github.com/facebookresearch/xformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"metaformer-baselines-for-vision","repo_url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/caformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"metaformer-baselines-for-vision","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":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"convnext","method_name":"ConvNeXt"},{"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":"metaformer","method_name":"MetaFormer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"poolformer","method_name":"PoolFormer"},{"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":"starrelu","method_name":"StarReLU"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[{"slug":"starrelu","name":"StarReLU","full_name":"StarReLU"}],"results":[{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"CAFormer-B36 (IN-21K, 384)","rank_in_archive_order":5,"of":39,"metrics":{"Number of params":"99M","Top-1 accuracy %":"79.5"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"ConvFormer-B36 (IN-21K, 384)","rank_in_archive_order":8,"of":39,"metrics":{"Number of params":"100M","Top-1 accuracy %":"73.5"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"CAFormer-B36 (IN-21K)","rank_in_archive_order":9,"of":39,"metrics":{"Number of params":"99M","Top-1 accuracy %":"69.4"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"ConvFormer-B36 (IN-21K)","rank_in_archive_order":12,"of":39,"metrics":{"Number of params":"100M","Top-1 accuracy %":"63.3"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"CAFormer-B36 (384)","rank_in_archive_order":14,"of":39,"metrics":{"Number of params":"99M","Top-1 accuracy %":"61.9"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"ConvFormer-B36 (384)","rank_in_archive_order":17,"of":39,"metrics":{"Number of params":"100M","Top-1 accuracy %":"55.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"CAFormer-B36","rank_in_archive_order":20,"of":39,"metrics":{"Number of params":"99M","Top-1 accuracy %":"48.5"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"ConvFormer-B36","rank_in_archive_order":23,"of":39,"metrics":{"Number of params":"100M","Top-1 accuracy %":"40.1"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-c","task":"Domain Generalization","dataset":"ImageNet-C","model":"CAFormer-B36 (IN21K, 384)","rank_in_archive_order":2,"of":47,"metrics":{"Number of params":"99M","mean Corruption Error (mCE)":"30.8"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-c","task":"Domain Generalization","dataset":"ImageNet-C","model":"CAFormer-B36 (IN21K)","rank_in_archive_order":5,"of":47,"metrics":{"mean Corruption Error (mCE)":"31.8"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-c","task":"Domain Generalization","dataset":"ImageNet-C","model":"ConvFormer-B36 (IN21K)","rank_in_archive_order":7,"of":47,"metrics":{"mean Corruption Error (mCE)":"35.0"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-c","task":"Domain Generalization","dataset":"ImageNet-C","model":"CAFormer-B36","rank_in_archive_order":18,"of":47,"metrics":{"mean Corruption Error (mCE)":"42.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-c","task":"Domain Generalization","dataset":"ImageNet-C","model":"ConvFormer-B36","rank_in_archive_order":23,"of":47,"metrics":{"mean Corruption Error (mCE)":"46.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset":"ImageNet-R","model":"CAFormer-B36 (IN21K, 384)","rank_in_archive_order":5,"of":39,"metrics":{"Top-1 Error Rate":"29.6"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset":"ImageNet-R","model":"CAFormer-B36 (IN21K)","rank_in_archive_order":7,"of":39,"metrics":{"Top-1 Error Rate":"31.7"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset":"ImageNet-R","model":"ConvFormer-B36 (IN21K, 384)","rank_in_archive_order":11,"of":39,"metrics":{"Top-1 Error Rate":"33.5"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset":"ImageNet-R","model":"ConvFormer-B36 (IN21K)","rank_in_archive_order":13,"of":39,"metrics":{"Top-1 Error Rate":"34.7"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset":"ImageNet-R","model":"CAFormer-B36 (384)","rank_in_archive_order":21,"of":39,"metrics":{"Top-1 Error Rate":"45"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset":"ImageNet-R","model":"CAFormer-B36","rank_in_archive_order":23,"of":39,"metrics":{"Top-1 Error Rate":"46.1"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset":"ImageNet-R","model":"ConvFormer-B36 (384)","rank_in_archive_order":24,"of":39,"metrics":{"Top-1 Error Rate":"47.8"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset":"ImageNet-R","model":"ConvFormer-B36","rank_in_archive_order":25,"of":39,"metrics":{"Top-1 Error Rate":"48.9"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-sketch","task":"Domain Generalization","dataset":"ImageNet-Sketch","model":"CAFormer-B36 (IN21K, 384)","rank_in_archive_order":5,"of":20,"metrics":{"Top-1 accuracy":"54.5"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-sketch","task":"Domain Generalization","dataset":"ImageNet-Sketch","model":"ConvFormer-B36 (IN21K, 384)","rank_in_archive_order":7,"of":20,"metrics":{"Top-1 accuracy":"52.9"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-sketch","task":"Domain Generalization","dataset":"ImageNet-Sketch","model":"CAFormer-B36 (IN21K)","rank_in_archive_order":8,"of":20,"metrics":{"Top-1 accuracy":"52.8"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-sketch","task":"Domain Generalization","dataset":"ImageNet-Sketch","model":"ConvFormer-B36 (IN21K)","rank_in_archive_order":9,"of":20,"metrics":{"Top-1 accuracy":"52.7"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-sketch","task":"Domain Generalization","dataset":"ImageNet-Sketch","model":"CAFormer-B36","rank_in_archive_order":17,"of":20,"metrics":{"Top-1 accuracy":"42.5"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-sketch","task":"Domain Generalization","dataset":"ImageNet-Sketch","model":"ConvFormer-B36","rank_in_archive_order":19,"of":20,"metrics":{"Top-1 accuracy":"39.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-B36 (384 res, 21K)","rank_in_archive_order":59,"of":1060,"metrics":{"GFLOPs":"72.2","Number of params":"99M","Top 1 Accuracy":"88.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-B36 (384 res, 21K)","rank_in_archive_order":79,"of":1060,"metrics":{"GFLOPs":"66.5","Number of params":"100M","Top 1 Accuracy":"87.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-M36 (384 res, 21K)","rank_in_archive_order":83,"of":1060,"metrics":{"GFLOPs":"42","Number of params":"56M","Top 1 Accuracy":"87.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-B36 (224 res, 21K)","rank_in_archive_order":93,"of":1060,"metrics":{"GFLOPs":"23.2","Number of params":"99M","Top 1 Accuracy":"87.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-B36 (224 res, 21K)","rank_in_archive_order":113,"of":1060,"metrics":{"GFLOPs":"22.6","Number of params":"100M","Top 1 Accuracy":"87.0%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-S36 (384 res, 21K)","rank_in_archive_order":116,"of":1060,"metrics":{"GFLOPs":"26.0","Number of params":"39M","Top 1 Accuracy":"86.9%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-M36 (384 res, 21K)","rank_in_archive_order":117,"of":1060,"metrics":{"GFLOPs":"37.7","Number of params":"57M","Top 1 Accuracy":"86.9%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-M36 (224 res, 21K)","rank_in_archive_order":132,"of":1060,"metrics":{"GFLOPs":"13.2","Number of params":"56M","Top 1 Accuracy":"86.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-S36 (384 res, 21K)","rank_in_archive_order":147,"of":1060,"metrics":{"GFLOPs":"22.4","Number of params":"40M","Top 1 Accuracy":"86.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-B36 (384 res)","rank_in_archive_order":150,"of":1060,"metrics":{"GFLOPs":"72.2","Number of params":"99M","Top 1 Accuracy":"86.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-M36 (384 res)","rank_in_archive_order":168,"of":1060,"metrics":{"GFLOPs":"42.0","Number of params":"56M","Top 1 Accuracy":"86.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-M36 (224 res, 21K)","rank_in_archive_order":173,"of":1060,"metrics":{"GFLOPs":"12.8","Number of params":"57M","Top 1 Accuracy":"86.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-S36 (224 res, 21K)","rank_in_archive_order":192,"of":1060,"metrics":{"GFLOPs":"8.0","Number of params":"39M","Top 1 Accuracy":"85.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-S36 (384 res)","rank_in_archive_order":209,"of":1060,"metrics":{"GFLOPs":"26.0","Number of params":"39M","Top 1 Accuracy":"85.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-B36 (384 res)","rank_in_archive_order":210,"of":1060,"metrics":{"GFLOPs":"66.5","Number of params":"100M","Top 1 Accuracy":"85.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-M36 (384 res)","rank_in_archive_order":214,"of":1060,"metrics":{"GFLOPs":"37.7","Number of params":"57M","Top 1 Accuracy":"85.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-B36 (224 res)","rank_in_archive_order":225,"of":1060,"metrics":{"GFLOPs":"23.2","Number of params":"99M","Top 1 Accuracy":"85.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-S18 (384 res, 21K)","rank_in_archive_order":231,"of":1060,"metrics":{"GFLOPs":"13.4","Number of params":"26M","Top 1 Accuracy":"85.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-S36 (224 res, 21K)","rank_in_archive_order":232,"of":1060,"metrics":{"GFLOPs":"7.6","Number of params":"40M","Top 1 Accuracy":"85.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-S36 (384 res)","rank_in_archive_order":233,"of":1060,"metrics":{"GFLOPs":"22.4","Number of params":"40M","Top 1 Accuracy":"85.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-M36 (224 res)","rank_in_archive_order":248,"of":1060,"metrics":{"GFLOPs":"13.2","Number of params":"56M","Top 1 Accuracy":"85.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-S18 (384 res)","rank_in_archive_order":267,"of":1060,"metrics":{"GFLOPs":"13.4","Number of params":"26M","Top 1 Accuracy":"85.0%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-S18 (384 res, 21K)","rank_in_archive_order":268,"of":1060,"metrics":{"GFLOPs":"11.6","Number of params":"27M","Top 1 Accuracy":"85.0%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-B36 (224 res)","rank_in_archive_order":291,"of":1060,"metrics":{"GFLOPs":"22.6","Number of params":"100M","Top 1 Accuracy":"84.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-S36 (224 res)","rank_in_archive_order":309,"of":1060,"metrics":{"GFLOPs":"8.0","Number of params":"39M","Top 1 Accuracy":"84.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-M36 (224 res)","rank_in_archive_order":311,"of":1060,"metrics":{"GFLOPs":"12.8","Number of params":"57M","Top 1 Accuracy":"84.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-S18 (384 res)","rank_in_archive_order":318,"of":1060,"metrics":{"GFLOPs":"11.6","Number of params":"27M","Top 1 Accuracy":"84.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-S18 (224 res, 21K)","rank_in_archive_order":353,"of":1060,"metrics":{"GFLOPs":"4.1","Number of params":"26M","Top 1 Accuracy":"84.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-S36 (224 res)","rank_in_archive_order":355,"of":1060,"metrics":{"GFLOPs":"7.6","Number of params":"40M","Top 1 Accuracy":"84.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-S18 (224 res, 21K)","rank_in_archive_order":394,"of":1060,"metrics":{"GFLOPs":"3.9","Number of params":"27M","Top 1 Accuracy":"83.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"CAFormer-S18 (224 res)","rank_in_archive_order":412,"of":1060,"metrics":{"GFLOPs":"4.1","Number of params":"26M","Top 1 Accuracy":"83.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ConvFormer-S18 (224 res)","rank_in_archive_order":478,"of":1060,"metrics":{"GFLOPs":"3.9","Number of params":"27M","Top 1 Accuracy":"83.0%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.13452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13452"}},"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/rwightman/pytorch-image-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Westlake-AI/openmixup","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Westlake-AI/MogaNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sail-sg/metaformer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://gitlab.com/birder/birder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sail-sg/poolformer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/caformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/xformers","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"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":"4dbed9d1ded8239d","entry":"basic_blocks","repo":"sail-sg/poolformer","repo_kind":"listed","path":"models/poolformer.py","file_url":"https://github.com/sail-sg/poolformer/blob/HEAD/models/poolformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4dbed9d1ded8239d"}},{"code_sha256_prefix":"b84f022af3d984dc","entry":"reshape_transform_resmlp","repo":"sail-sg/poolformer","repo_kind":"listed","path":"misc/cam_image.py","file_url":"https://github.com/sail-sg/poolformer/blob/HEAD/misc/cam_image.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b84f022af3d984dc"}},{"code_sha256_prefix":"145f9f895f57722f","entry":"reshape_transform_swin","repo":"sail-sg/poolformer","repo_kind":"listed","path":"misc/cam_image.py","file_url":"https://github.com/sail-sg/poolformer/blob/HEAD/misc/cam_image.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"145f9f895f57722f"}},{"code_sha256_prefix":"9b13f431e8787323","entry":"reshape_transform_vit","repo":"sail-sg/poolformer","repo_kind":"listed","path":"misc/cam_image.py","file_url":"https://github.com/sail-sg/poolformer/blob/HEAD/misc/cam_image.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b13f431e8787323"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}