mlsanityData to 14 Oct 2026

Group Orthogonalization Regularization For Vision Models Adaptation and Robustness

arXiv 2306.10001 ↗First posted 16 Jun 2023cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 42 of its 58 references that are in the map. First posted on arXiv 16 Jun 2023.

Builds on

42 of 58 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2023Segment Anythingcited by 8,234
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  10. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  11. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  12. 2016Layer Normalizationcited by 5,669
30 more
  1. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  2. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  3. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  5. 2016Wide Residual Networkscited by 3,070
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  8. 2018Group Normalizationcited by 1,524
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  11. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  12. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 719
  13. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  14. 2019Adversarial Training for Free!cited by 643
  15. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 543
  16. 2021Compacter: Efficient Low-Rank Hypercomplex Adapter Layerscited by 460
  17. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  18. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 243
  19. 2019Orthogonal Convolutional Neural Networkscited by 123
  20. 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 95
  21. 2015Reducing Overfitting in Deep Networks by Decorrelating Representationscited by 94
  22. 2017Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networkscited by 92
  23. 2017All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulationcited by 58
  24. 2022FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Contextcited by 49
  25. 2016Improving training of deep neural networks via Singular Value Boundingcited by 26
  26. 2017Combining Weakly and Webly Supervised Learning for Classifying Food Imagescited by 17
  27. 2016Optimization on Submanifolds of Convolution Kernels in CNNscited by 15
  28. 2020Orthogonal Deep Models As Defense Against Black-Box Attackscited by 7
  29. 2021An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networkscited by 7
  30. 2021Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Frameworkcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Non-Negative Stiefel Approximating Flow: Orthogonalish Matrix Optimization for Interpretable Embeddingscited by 1
  2. 2026RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
  2. 2023Statistical Guarantees of Group-Invariant GANs
  3. 2024Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization
  4. 2025Diffusion Models are Robust Pretrainers
  5. 2023Experts Weights Averaging: A New General Training Scheme for Vision Transformers
  6. 2025Mixture of Group Experts for Learning Invariant Representations
  7. 2024Regularization for Adversarial Robust Learning
  8. 2020Towards Robust Neural Networks via Orthogonal Diversity