Scale variation is a fundamental challenge in computer vision. Objects of the same class can have different sizes, and their perceived size is further affected by the distance from the camera. These variations are local to the objects, i.e., different object sizes may change differently within the same image. To effectively handle scale variations, we present a deep equilibrium canonicalizer (DEC) to improve the local scale equivariance of a model. DEC can be easily incorporated into existing network architectures and can be adapted to a pre-trained model. Notably, we show that on the competitive ImageNet benchmark, DEC improves both model performance and local scale consistency across four popular pre-trained deep-nets, e.g., ViT, DeiT, Swin, and BEiT. Our code is available at https://github.com/ashiq24/local-scale-equivariance.
@article{arxiv.2508.14187,
title = {Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer},
author = {Md Ashiqur Rahman and Chiao-An Yang and Michael N. Cheng and Lim Jun Hao and Jeremiah Jiang and Teck-Yian Lim and Raymond A. Yeh},
journal= {arXiv preprint arXiv:2508.14187},
year = {2025}
}