SpiralMLP: A Lightweight Vision MLP Architecture
This work addresses the need for lightweight and efficient vision models for computer vision applications, offering an incremental improvement over existing MLP-based methods.
The paper tackles the challenge of designing efficient vision architectures by introducing SpiralMLP, which uses a Spiral FC layer to replace token mixing, achieving state-of-the-art performance on benchmarks like ImageNet-1k, COCO, and ADE20K with linear computational complexity.
We present SpiralMLP, a novel architecture that introduces a Spiral FC layer as a replacement for the conventional Token Mixing approach. Differing from several existing MLP-based models that primarily emphasize axes, our Spiral FC layer is designed as a deformable convolution layer with spiral-like offsets. We further adapt Spiral FC into two variants: Self-Spiral FC and Cross-Spiral FC, which enable both local and global feature integration seamlessly, eliminating the need for additional processing steps. To thoroughly investigate the effectiveness of the spiral-like offsets and validate our design, we conduct ablation studies and explore optimal configurations. In empirical tests, SpiralMLP reaches state-of-the-art performance, similar to Transformers, CNNs, and other MLPs, benchmarking on ImageNet-1k, COCO and ADE20K. SpiralMLP still maintains linear computational complexity O(HW) and is compatible with varying input image resolutions. Our study reveals that targeting the full receptive field is not essential for achieving high performance, instead, adopting a refined approach offers better results.