MLP-Mixer: An all-MLP Architecture for Vision

Explore this paper's citation graph

Summary

It is shown that while convolutions and attention are both sufficient for good performance, neither of them are necessary, and MLP-Mixer, an architecture based exclusively on multi-layer perceptrons (MLPs), attains competitive scores on image classification benchmarks.

Type
preprint
Published
2021-05-04
Cited by
3,780
References
65
Access
Open access

Keywords

Computer science, Artificial intelligence, Convolutional neural network, Perceptron, Pattern recognition (psychology)

References

Cited by

Related papers