mlsanityData to 7 Oct 2026

Bootstrap Generalization Ability from Loss Landscape Perspective

arXiv 2209.08473 ↗First posted 18 Sep 2022cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Domain generalization aims to learn a model that can generalize well on the unseen test dataset, i.e., out-of-distribution data, which has different distribution from the training dataset. To address domain generalization in computer vision, we introduce the loss landscape theory into this field. Specifically, we bootstrap the generalization ability of the deep learning model from the loss landscape perspective in four aspects, including backbone, regularization, training paradigm, and learning rate. We verify the proposed theory on the NICO++, PACS, and VLCS datasets by doing extensive ablation studies as well as visualizations. In addition, we apply this theory in the ECCV 2022 NICO Challenge1 and achieve the 3rd place without using any domain invariant methods.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 54 of its 66 references that are in the map. First posted on arXiv 18 Sep 2022.

Builds on

54 of 66 references.

References · 54

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  8. 2016Wide Residual Networkscited by 3,057
  9. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  10. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  11. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  12. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
38 more
  1. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  2. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  3. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
  4. 2020In Search of Lost Domain Generalizationcited by 1,042
  5. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  6. 2016Least Squares Generative Adversarial Networkscited by 1,000
  7. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  8. 2016Deep Networks with Stochastic Depthcited by 973
  9. 2020Designing Network Design Spacescited by 954
  10. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  11. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 748
  12. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  13. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  14. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  15. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  16. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  17. 2016Domain Separation Networkscited by 317
  18. 2021ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networkscited by 293
  19. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  20. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  21. 2019Episodic Training for Domain Generalizationcited by 245
  22. 2018A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decaycited by 223
  23. 2015The Power of Depth for Feedforward Neural Networkscited by 181
  24. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  25. 2021Learning to Diversify for Single Domain Generalizationcited by 170
  26. 2016Deep Pyramidal Residual Networkscited by 163
  27. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  28. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  29. 2021Efficient Sharpness-aware Minimization for Improved Training of Neural Networkscited by 137
  30. 2020Learning to Balance Specificity and Invariance for In and Out of Domain Generalizationcited by 128
  31. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  32. 2018Robust Classification with Convolutional Prototype Learningcited by 122
  33. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  34. 2020Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustnesscited by 121
  35. 2022Sharpness-Aware Training for Freecited by 95
  36. 2017Shake-Shake regularizationcited by 87
  37. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  38. 2018Best sources forward: domain generalization through source-specific netscited by 81

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 7; 2025: 2; 2026: 2.

16 papers.

Sort:

By area:

  1. 2023Rethinking Model Ensemble in Transfer-based Adversarial Attackscited by 88
  2. 2024Elucidating the Design Space of Dataset Condensationcited by 40
  3. 2025A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1cited by 34
  4. 2024On the Duality Between Sharpness-Aware Minimization and Adversarial Trainingcited by 24
  5. 2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 22
  6. 2024Rethinking Centered Kernel Alignment in Knowledge Distillationcited by 17
  7. 2024CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTscited by 17
  8. 2025V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMscited by 9
  9. 2023Digital Twin-Enhanced Deep Reinforcement Learning for Resource Management in Networks Slicingcited by 7
  10. 2022Teaching What You Should Teach: A Data-Based Distillation Methodcited by 5
  11. 2026Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targetingcited by 5
  12. 2023AFN: Adaptive Fusion Normalization via an Encoder-Decoder Frameworkcited by 2
4 more
  1. 2023Enhancing Adversarial Attacks: The Similar Target Methodcited by 1
  2. 2026Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMscited by 1
  3. 2024Sparse Color-Code Net: Real-Time RGB-Based 6D Object Pose Estimation on Edge Devicescited by 0
  4. 2024rECGnition_v1.0: Arrhythmia detection using cardiologist-inspired multi-modal architecture incorporating demographic attributes in ECGcited by 0