MetaFormer is Actually What You Need for Vision

by   Weihao Yu, et al.

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 the most 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 vision transformer/MLP-like baselines DeiT-B/ResMLP-B24 by 0.3 with 35 PoolFormer 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. Code is available at


page 1

page 2

page 3

page 4


UniNeXt: Exploring A Unified Architecture for Vision Recognition

Vision Transformers have shown great potential in computer vision tasks....

SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation

Recent studies show that self-attentions behave like low-pass filters (a...

iMixer: hierarchical Hopfield network implies an invertible, implicit and iterative MLP-Mixer

In the last few years, the success of Transformers in computer vision ha...

SepTr: Separable Transformer for Audio Spectrogram Processing

Following the successful application of vision transformers in multiple ...

Do We Really Need Explicit Position Encodings for Vision Transformers?

Almost all visual transformers such as ViT or DeiT rely on predefined po...

Attention Hijacking in Trojan Transformers

Trojan attacks pose a severe threat to AI systems. Recent works on Trans...

Demystify Transformers Convolutions in Modern Image Deep Networks

Recent success of vision transformers has inspired a series of vision ba...

Please sign up or login with your details

Forgot password? Click here to reset