The DOI matches its Crossref record; 63 of the 63 references it cites were found in a registry or an index.
MetaFormer is Actually What You Need for Vision
Open accessAbstract
Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in transformers with an embarrassingly simple spatial pooling operator to conduct only basic token mixing. Surprisingly, we observe that the derived model, termed as PoolFormer, achieves competitive performance on multiple computer vision tasks. For example, on ImageNet-1K, PoolFormer achieves 82.1 % top-1 accuracy, surpassing well-tuned vision transformer/MLP-like baselines DeiT-B/ResMLP-B24 by 0.3%/1.1% accuracy with 35%/52% fewer parameters and 49%/61% fewer MACs. The effectiveness of Pool-Former verifies our hypothesis and urges us to initiate the concept of “MetaFormer”, a general architecture abstracted from transformers without specifying the token mixer. Based on the extensive experiments, we argue that MetaFormer is the key player in achieving superior results for recent transformer and MLP-like models on vision tasks. This work calls for more future research dedicated to improving MetaFormer instead of focusing on the token mixer modules. Additionally, our proposed PoolFormer could serve as a starting baseline for future MetaFormer architecture design.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Research works printed but not linked: 14
- liu, 2021, Pay attention to mlps, ArXiv Preprint
- lei ba, 2016, Layer normalization, ArXiv Preprint
- hou, 2021, Vision permutator: A permutable mlp-like architecture for visual recognition, ArXiv Preprint
- touvron, 0, Training data-efficient image transformers & distillation through attention, International Conference on Machine Learning, 10347
- wightman, 2021, Resnet strikes back: An improved training procedure in timm, ArXiv Preprint
- wightman, 2019, pytorch-image-models
- vaswani, 0, Attention is all you need, Advances in neural information processing systems, 5998
- contributors, 2020, MMSegmentation Openmmlab semantic segmentation toolbox and benchmark
- d'ascoli, 2021, Convit: Improving vision transformers with soft convolutional inductive biases, Proceedings of the 38th International Conference on Machine Learning volume 139 of Proceedings of Machine Learning Research, 2286
- dong, 2021, Attention is not all you need: Pure attention loses rank doubly exponentially with depth, ArXiv Preprint
- dosovitskiy, 0, An image is worth 16×16 words: Transformers for image recognition at scale, International Conference on Learning Representations
- chen, 2018, A^ 2-nets: Double attention networks, Advances in neural information processing systems, 31, 352
- raghu, 2021, Do vision transformers see like convolutional neural networks?, ArXiv Preprint
- rao, 2021, Global filter networks for image classification, ArXiv Preprint
Cited by
Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
Chen, J., Kao, S.-H., He, H., Zhuo, W., Wen, S., Lee, C.-H., & Chan, S.-H. G. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01157 · Cited by 2,343
Scaling Up Your Kernels to 31×31: Revisiting Large Kernel Design in CNNs
Ding, X., Zhang, X., Han, J., & Ding, G. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01166 · Cited by 1,447
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., Li, H., et al. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01385 · Cited by 1,080
Self-citationGuo, M.-H., Lu, C.-Z., Liu, Z.-N., Cheng, M.-M., & Hu, S.-M. (2023) · Computational Visual Media · doi:10.1007/s41095-023-0364-2 · Cited by 1,073
EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention
Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., & Yuan, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01386 · Cited by 956
Large Selective Kernel Network for Remote Sensing Object Detection
Li, Y., Hou, Q., Zheng, Z., Cheng, M.-M., Yang, J., & Li, X. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01540 · Cited by 893
Rep ViT: Revisiting Mobile CNN From ViT Perspective
Wang, A., Chen, H., Lin, Z., Han, J., & Ding, G. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01506 · Cited by 752
“For example, lightweight ViTs usually adopt the MetaFormer block structure [69], while lightweight CNNs favors the inverted residual bottleneck [53].”
BackgroundInfluentialA Survey of Visual Transformers
Liu, Y., Zhang, Y., Wang, Y., Hou, F., Yuan, J., Tian, J., Zhang, Y., Shi, Z., Fan, J., & He, Z. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3227717 · Cited by 549
MedViT: A robust vision transformer for generalized medical image classification
Manzari, O. N., Ahmadabadi, H., Kashiani, H., Shokouhi, S. B., & Ayatollahi, A. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106791 · Cited by 526
EMCAD: Efficient Multi-Scale Convolutional Attention Decoding for Medical Image Segmentation
Rahman, M. M., Munir, M., & Marculescu, R. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01118 · Cited by 524
Advances in medical image analysis with vision Transformers: A comprehensive review
Azad, R., Kazerouni, A., Heidari, M., Aghdam, E. K., Molaei, A., Jia, Y., Jose, A., Roy, R., & Merhof, D. (2024) · Medical Image Analysis · doi:10.1016/j.media.2023.103000 · Cited by 485
InceptionNeXt: When Inception Meets ConvNeXt
Yu, W., Zhou, P., Yan, S., & Wang, X. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00542 · Cited by 423
Self-citationEdgenext: Efficiently amalgamated CNN-transformer architecture for mobile vision applications
Maaz, M., Shaker, A., Cholakkal, H., Khan, S., Zamir, S. W., Anwer, R. M., & Shahbaz Khan, F. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-25082-8_1 · Cited by 407
DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition
Jiao, J., Tang, Y.-M., Lin, K.-Y., Gao, Y., Ma, A. J., Wang, Y., & Zheng, W.-S. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3243616 · Cited by 398
Li, J., Chen, J., Tang, Y., Wang, C., Landman, B. A., & Zhou, S. K. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102762 · Cited by 389
MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Hatamizadeh, A., & Kautz, J. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.02352 · Cited by 358
Centralized Feature Pyramid for Object Detection
Quan, Y., Zhang, D., Zhang, L., & Tang, J. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3297408 · Cited by 342
MetaFormer Baselines for Vision
Yu, W., Si, C., Zhou, P., Luo, M., Zhou, Y., Feng, J., Yan, S., & Wang, X. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3329173 · Cited by 331
Self-citationRethinking Vision Transformers for MobileNet Size and Speed
Li, Y., Hu, J., Wen, Y., Evangelidis, G., Salahi, K., Wang, Y., Tulyakov, S., & Ren, J. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01549 · Cited by 329
Rethinking Mobile Block for Efficient Attention-based Models
Zhang, J., Li, X., Li, J., Liu, L., Xue, Z., Zhang, B., Jiang, Z., Huang, T., Wang, Y., & Wang, C. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00134 · Cited by 313
Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution
Sun, L., Dong, J., Tang, J., & Pan, J. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01213 · Cited by 289
SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
Shaker, A., Maaz, M., Rasheed, H., Khan, S., Yang, M.-H., & Khan, F. S. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01598 · Cited by 279
ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond
Zhang, Q., Xu, Y., Zhang, J., & Tao, D. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-022-01739-w · Cited by 277
How Do Vision Transformers Work?
Park, N., & Kim, S. (2022) · arXiv · doi:10.48550/arxiv.2202.06709 · Cited by 356
“The most widely accepted explanation for the success of MSAs is their weak inductive bias and capture of long-range dependencies (See, e.g., (Dosovitskiy et al., 2021; Naseer et al., 2021; Tuli et al., 2021; Yu et al., 2021; Mao et al., 2021; Chu et al., 2021)).”
BackgroundA Lightweight IoT Intrusion Detection Model Based on Improved BERT-of-Theseus
Wang, Z., Li, J., Yang, S., Luo, X., Li, D., & Mahmoodi, S. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122045 · Cited by 131
NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results
Li, Y., Zhang, Y., Timofte, R., Van Gool, L., Yu, L., Li, Y., Li, X., Jiang, T., Wu, Q., Han, M., et al. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00189 · Cited by 72
Self-citationPersonalized federated learning for buildings energy consumption forecasting
Wang, R., Bai, L., Rayhana, R., & Liu, Z. (2024) · Energy and Buildings · doi:10.1016/j.enbuild.2024.114762 · Cited by 38
Dai, Y., Zheng, T., Xue, C., & Zhou, L. (2022) · Remote Sensing · doi:10.3390/rs14246297 · Cited by 35
Dancing in the Dark: A Benchmark towards General Low-light Video Enhancement
Fu, H., Zheng, W., Wang, X., Wang, J., Zhang, H., & Ma, H. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01183 · Cited by 33
Self-citationTFormer: A Transmission-Friendly ViT Model for IoT Devices
Lu, Z., Ding, C., Juefei-Xu, F., Boddeti, V. N., Wang, S., & Yang, Y. (2023) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2022.3222765 · Cited by 24
RWKV: Reinventing RNNs for the Transformer Era
Peng, B., Alcaide, E., Anthony, Q., Albalak, A., Arcadinho, S., Biderman, S., Cao, H., Cheng, X., Chung, M., Grella, M., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.13048 · Cited by 17
“FFN with R gate Prior research (Tolstikhin et al., 2021; Liu et al., 2021; Yu et al., 2022) suggests that self-attention may not be as essential in Transformer-based vision tasks as previously thought.”
MethodSelf-citationAWaveFormer: Audio Wavelet Transformer Network for Generalized Audio Deepfake Detection
Wang, R., Chen, Z., Wang, B., Ba, Z., & Ren, K. (2025) · IEEE Transactions on Audio, Speech and Language Processing · doi:10.1109/taslpro.2025.3611229 · Cited by 10
Metadata
- Authors
- Yu, W., Luo, M., Zhou, P., Si, C., Zhou, Y., Wang, X., Feng, J., & Yan, S.
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 10809-10819
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4312820606
- Cited by
- 1,255
- References
- 63
- FWCI
- 103.05
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.