paper-with-me

Papers

Soft Equivariance Regularization for Invariant Self-Supervised Learning

2026-03-04 · Joohyung Lee, Changhun Kim, Hyunsu Kim, Kwanhyung Lee, Juho Lee arxiv

Self-supervised learning (SSL) typically learns representations invariant to semantic-preserving augmentations. While effective for recognition, enforcing strong invariance can suppress transformation-dependent structure that is useful for robustness to geometric perturbations and spatially sensitive transfer. A growing body of work, therefore, augments invariance-based SSL with equivariance objectives, but these objectives are often imposed on the same final representation. We empirically observe a trade-off in this coupled setting: pushing equivariance regularization toward deeper layers improves equivariance scores but degrades ImageNet-1k linear evaluation, motivating a layer-decoupled design. Motivated by this trade-off, we propose Soft Equivariance Regularization (SER), a plug-in regularizer that decouples where invariance and equivariance are enforced: we keep the base SSL objective unchanged on the final embedding, while softly encouraging equivariance on an intermediate spatial token map via analytically specified group actions $ρ_g$ applied directly in feature space. SER learns/predicts no per-sample transformation codes/labels, requires no auxiliary transformation-prediction head, and adds only 1.008x training FLOPs. On ImageNet-1k ViT-S/16 pretraining, SER improves MoCo-v3 by +0.84 Top-1 in linear evaluation under a strictly matched 2-view setting and consistently improves DINO and Barlow Twins; under matched view counts, SER achieves the best ImageNet-1k linear-eval Top-1 among the compared invariance+equivariance add-ons. SER further improves ImageNet-C/P by +1.11/+1.22 Top-1 and frozen-backbone COCO detection by +1.7 mAP. Finally, applying the same layer-decoupling recipe to existing invariance+equivariance baselinesimproves their accuracy, suggesting layer decoupling as a general design principle for combining invariance and equivariance.

📄 PDF Abstract BibTeX arXiv:2603.06693

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

Self-Supervised Learning for Group Equivariant Neural Networks

2023-03-08 · Yusuke Mukuta, Tatsuya Harada

This paper proposes a method to construct pretext tasks for self-supervised learning on group equivariant neural networks. Group equivariant neural networks are the models whose structure is restricted to commute with th…

Self-Supervised Learning

Revisiting Consistency Regularization for Semi-Supervised Learning

2021-12-10 · Yue Fan, Anna Kukleva, Bernt Schiele

Consistency regularization is one of the most widely-used techniques for semi-supervised learning (SSL). Generally, the aim is to train a model that is invariant to various data augmentations. In this paper, we revisit t…

Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations

2021-09-29 · ICLR 2022 4 · Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han 외

In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, th…

Self-Supervised Learning

A Regularization-Guided Equivariant Approach for Image Restoration

2025-05-26 · CVPR 2025 1 · Yulu Bai, Jiahong Fu, Qi Xie, Deyu Meng

Equivariant and invariant deep learning models have been developed to exploit intrinsic symmetries in data, demonstrating significant effectiveness in certain scenarios. However, these methods often suffer from limited r…

Data AugmentationImage RestorationSelf-Supervised Learning

Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors

2023-09-28 · ICCV 2023 1 · Yuanyi Zhong, Anand Bhattad, Yu-Xiong Wang, David Forsyth

Dense depth and surface normal predictors should possess the equivariant property to cropping-and-resizing -- cropping the input image should result in cropping the same output image. However, we find that state-of-the-a…

Data Augmentation