MLP-Mixer: An all-MLP Architecture for Vision

Autor:	Tolstikhin, Ilya, Houlsby, Neil, Kolesnikov, Alexander, Beyer, Lucas, Zhai, Xiaohua, Unterthiner, Thomas, Yung, Jessica, Steiner, Andreas, Keysers, Daniel, Uszkoreit, Jakob, Lucic, Mario, Dosovitskiy, Alexey
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Convolutional Neural Networks (CNNs) are the go-to model for computer vision. Recently, attention-based networks, such as the Vision Transformer, have also become popular. In this paper we show that while convolutions and attention are both sufficient for good performance, neither of them are necessary. We present MLP-Mixer, an architecture based exclusively on multi-layer perceptrons (MLPs). MLP-Mixer contains two types of layers: one with MLPs applied independently to image patches (i.e. "mixing" the per-location features), and one with MLPs applied across patches (i.e. "mixing" spatial information). When trained on large datasets, or with modern regularization schemes, MLP-Mixer attains competitive scores on image classification benchmarks, with pre-training and inference cost comparable to state-of-the-art models. We hope that these results spark further research beyond the realms of well established CNNs and Transformers. Comment: v2: Fixed parameter counts in Table 1. v3: Added results on JFT-3B in Figure 2(right); Added Section 3.4 on the input permutations. v4: Updated the x label in Figure 2(right)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2105.01601 Zobrazit plný text záznamu View this record from Arxiv