Group Orthogonalization Regularization For Vision Models Adaptation and Robustness

2023-06-16 · Yoav Kurtz, Noga Bar, Raja Giryes

As neural networks become deeper, the redundancy within their parameters increases. This phenomenon has led to several methods that attempt to reduce the correlation between convolutional filters. We propose a computationally efficient regularization technique that encourages orthonormality between groups of filters within the same layer. Our experiments show that when incorporated into recent adaptation methods for diffusion models and vision transformers (ViTs), this regularization improves performance on downstream tasks. We further show improved robustness when group orthogonality is enforced during adversarial training. Our code is available at https://github.com/YoavKurtz/GOR.

📄 PDF Abstract BibTeX arXiv:2306.10001

Code (1)

yoavkurtz/gor 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models

2026-05-14 · Yuehao Liu, Shanyan Guan, Weijia Zhang, Xuanming Shang 외 arxiv

Continual learning in multimodal large language models (MLLMs) aims to sequentially acquire knowledge while mitigating catastrophic forgetting, yet existing methods face inherent limitations: architecture-based approache…

Continual Learning

An Analysis of SVD for Deep Rotation Estimation

2020-06-25 · NeurIPS 2020 12 · Jake Levinson, Carlos Esteves, Kefan Chen, Noah Snavely 외

Symmetric orthogonalization via SVD, and closely related procedures, are well-known techniques for projecting matrices onto $O(n)$ or $SO(n)$. These tools have long been used for applications in computer vision, for exam…

3D Pose Estimation 3D Rotation Estimation Pose Estimation

unORANIC: Unsupervised Orthogonalization of Anatomy and Image-Characteristic Features

2023-08-29 · Sebastian Doerrich, Francesco Di Salvo, Christian Ledig

We introduce unORANIC, an unsupervised approach that uses an adapted loss function to drive the orthogonalization of anatomy and image-characteristic features. The method is versatile for diverse modalities and tasks, as…

Anatomy Medical Image Analysis

Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100

2021-08-05 · ICLR 2022 4 · Sahil Singla, Surbhi Singla, Soheil Feizi

Training convolutional neural networks (CNNs) with a strict Lipschitz constraint under the $l_{2}$ norm is useful for provable adversarial robustness, interpretable gradients and stable training. While $1$-Lipschitz CNNs…

Adversarial Robustness

Robust Object Detection for Autonomous Driving via Curriculum-Guided Group Relative Policy Optimization

2025-09-19 · Xu Jia arxiv

Multimodal Large Language Models (MLLMs) excel in vision-language reasoning but often struggle with structured perception tasks requiring precise localization and robustness. We propose a reinforcement learning framework…

Robust Object Detection Reinforcement Learning Autonomous Driving