English

Spectral-Adaptive Modulation Networks for Visual Perception

Computer Vision and Pattern Recognition 2026-05-13 v2

Abstract

Recent studies have shown that 2D convolution and self-attention exhibit distinct spectral behaviors, and optimizing their spectral properties can enhance vision model performance. However, theoretical analyses remain limited in explaining why 2D convolution is more effective in high-pass filtering than self-attention and why larger kernels favor shape bias, akin to self-attention. In this paper, we employ graph spectral analysis to theoretically simulate and compare the frequency responses of 2D convolution and self-attention within a unified framework. Our results corroborate previous empirical findings and reveal that node connectivity, modulated by window size, is a key factor in shaping spectral functions. Leveraging this insight, we introduce a \textit{spectral-adaptive modulation} (SPAM) mixer, which processes visual features in a spectral-adaptive manner using multi-scale convolutional kernels and a spectral re-scaling mechanism to refine spectral components. Based on SPAM, we develop SPANetV2 as a novel vision backbone. Extensive experiments demonstrate that SPANetV2 outperforms state-of-the-art models across multiple vision tasks, including ImageNet-1K classification, COCO object detection, and ADE20K semantic segmentation.

Keywords

Cite

@article{arxiv.2503.23947,
  title  = {Spectral-Adaptive Modulation Networks for Visual Perception},
  author = {Guhnoo Yun and Juhan Yoo and Kijung Kim and Jeongho Lee and Paul Hongsuck Seo and Dong Hwan Kim},
  journal= {arXiv preprint arXiv:2503.23947},
  year   = {2026}
}

Comments

Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

R2 v1 2026-06-28T22:40:22.207Z