English

Tunable Soft Equivariance with Guarantees

Computer Vision and Pattern Recognition 2026-03-30 v1 Machine Learning

Abstract

Equivariance is a fundamental property in computer vision models, yet strict equivariance is rarely satisfied in real-world data, which can limit a model's performance. Controlling the degree of equivariance is therefore desirable. We propose a general framework for constructing soft equivariant models by projecting the model weights into a designed subspace. The method applies to any pre-trained architecture and provides theoretical bounds on the induced equivariance error. Empirically, we demonstrate the effectiveness of our method on multiple pre-trained backbones, including ViT and ResNet, across image classification, semantic segmentation, and human-trajectory prediction tasks. Notably, our approach improves the performance while simultaneously reducing equivariance error on the competitive ImageNet benchmark.

Keywords

Cite

@article{arxiv.2603.26657,
  title  = {Tunable Soft Equivariance with Guarantees},
  author = {Md Ashiqur Rahman and Lim Jun Hao and Jeremiah Jiang and Teck-Yian Lim and Raymond A. Yeh},
  journal= {arXiv preprint arXiv:2603.26657},
  year   = {2026}
}
R2 v1 2026-07-01T11:41:15.720Z