CycleMLP: A MLP-Like Architecture for Dense Visual Predictions
Top Cited Papers
- 8 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14284-14300
Abstract
This article presents a simple yet effective multilayer perceptron (MLP) architecture, namely CycleMLP, which is a versatile neural backbone network capable of solving various tasks of dense visual predictions such as object detection, segmentation, and human pose estimation. Compared to recent advanced MLP architectures such as MLP-Mixer (Tolstikhin et al. 2021), ResMLP (Touvron et al. 2021), and gMLP (Liu et al. 2021), whose architectures are sensitive to image size and are infeasible in dense prediction tasks, CycleMLP has two appealing advantages: 1) CycleMLP can cope with various spatial sizes of images; 2) CycleMLP achieves linear computational complexity with respect to the image size by using local windows. In contrast, previous MLPs have $O(N^{2})$ computational complexity due to their full connections in space. 3) The relationship between convolution, multi-head self-attention in Transformer, and CycleMLP are discussed through an intuitive theoretical analysis. We build a family of models that can surpass state-of-the-art MLP and Transformer models e.g., Swin Transformer (Liu et al. 2021), while using fewer parameters and FLOPs. CycleMLP expands the MLP-like models’ applicability, making them versatile backbone networks that achieve competitive results on dense prediction tasks For example, CycleMLP-Tiny outperforms Swin-Tiny by 1.3% mIoU on ADE20 K dataset with fewer FLOPs. Moreover, CycleMLP also shows excellent zero-shot robustness on ImageNet-C dataset.
Keywords
All Related Versions
Funding Information
- National Key R&D Program of China (2022ZD0161000)
- General Research Fund of Hong Kong (17200622)
This publication has 62 references indexed in Scilit:
- Aggregated Residual Transformations for Deep Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Rethinking the Inception Architecture for Computer Vision2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Going deeper with convolutions2015
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- An Algorithm for the Machine Calculation of Complex Fourier SeriesMathematics of Computation, 1965
- The perceptron: A probabilistic model for information storage and organization in the brain.Psychological Review, 1958