Cyclemlp: A MLP-like architecture for dense prediction

Abstract

This paper presents a simple MLP-like architecture, CycleMLP, which is a versatile backbone for visual recognition and dense predictions. As compared to modern MLP architectures, e.g. , MLP-Mixer (Tolstikhin et al., 2021), ResMLP (Touvron et al., 2021a), and gMLP (Liu et al., 2021a), whose architectures are correlated to image size and thus are infeasible in object detection and segmentation, CycleMLP has two advantages compared to modern approaches. (1) It can cope with various image sizes. (2) It achieves linear computational complexity to image size by using local windows. In contrast, previous MLPs have O(N2) computations due to fully spatial connections. We build a family of models which surpass existing MLPs and even state-of-the-art Transformer-based models, e.g. Swin Transformer (Liu et al., 2021b), while using fewer parameters and FLOPs. We expand the MLP-like models’ applicability, making them a versatile backbone for dense prediction tasks. CycleMLP achieves competitive results on object detection, instance segmentation, and semantic segmentation. In particular, CycleMLP-Tiny outperforms Swin-Tiny by 1.3% mIoU on ADE20K dataset with fewer FLOPs. Moreover, CycleMLP also shows excellent zero-shot robustness on ImageNet-C dataset.