Domain Generalization with Vital Phase Augmentation
Abstract: Deep neural networks have shown remarkable performance in image classification. However, their performance significantly deteriorates with corrupted input data. Domain generalization methods have been proposed to train robust models against out-of-distribution data. Data augmentation in the frequency domain is one of such approaches that enable a model to learn phase features to establish domain-invariant representations. This approach changes the amplitudes of the input data while preserving the phases. However, using fixed phases leads to susceptibility to phase fluctuations because amplitudes and phase fluctuations commonly occur in out-of-distribution. In this study, to address this problem, we introduce an approach using finite variation of the phases of input data rather than maintaining fixed phases. Based on the assumption that the degree of domain-invariant features varies for each phase, we propose a method to distinguish phases based on this degree. In addition, we propose a method called vital phase augmentation (VIPAug) that applies the variation to the phases differently according to the degree of domain-invariant features of given phases. The model depends more on the vital phases that contain more domain-invariant features for attaining robustness to amplitude and phase fluctuations. We present experimental evaluations of our proposed approach, which exhibited improved performance for both clean and corrupted data. VIPAug achieved SOTA performance on the benchmark CIFAR-10 and CIFAR-100 datasets, as well as near-SOTA performance on the ImageNet-100 and ImageNet datasets. Our code is available at https://github.com/excitedkid/vipaug.
- Amplitude-phase recombination: Rethinking robustness of convolutional neural networks in frequency domain. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 458–467.
- Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In International Conference on Machine Learning, 2206–2216. PMLR.
- AutoAugment: Learning augmentation policies from data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 113–123.
- ImageNet: A large-scale hierarchical image database. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 248–255.
- Improved regularization of convolutional neural networks with cutout. arXiv:1708.04552.
- Deep domain generalization with structured low-rank constraint. IEEE Transactions on Image Processing, 27(1): 304–313.
- An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations.
- Deep residual learning for image recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 770–778.
- Benchmarking neural network robustness to common corruptions and perturbations. In International Conference on Learning Representations.
- AugMix: A simple data processing method to improve robustness and Uncertainty. In International Conference on Learning Representations.
- PixMix: Dreamlike pictures comprehensively improve safety measures. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 16783–16792.
- Learning multiple layers of features from tiny images. Technical Report TR-2009, Dept. of Computer Science, Toronto Univ.
- ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25.
- Adversarial attack for asynchronous event-based data. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 1237–1244.
- Robust deep learning object recognition models rely on low frequency information in natural images. PLOS Computational Biology, 19(3): e1010932.
- MS-Net: multi-site network for improving prostate segmentation with heterogeneous MRI data. IEEE Transactions on Medical Imaging, 39(9): 2713–2724.
- Improving robustness without sacrificing accuracy with patch gaussian augmentation. arXiv:1906.02611.
- PRIME: A few primitives can boost robustness to common corruptions. In Proceedings of the European Conference on Computer Vision, 623–640. Springer.
- Unified deep supervised domain adaptation and generalization. In Proceedings of the IEEE International Conference on Computer Vision, 5715–5725.
- Playing for data: Ground truth from computer games. In Proceedings of the European Conference on Computer Vision, 102–118. Springer.
- A simple way to make neural networks robust against diverse image corruptions. In Proceedings of the European Conference on Computer Vision, 53–69. Springer.
- EfficientNet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning, 6105–6114. PMLR.
- Fast is better than free: Revisiting adversarial training. In International Conference on Learning Representations.
- A fourier-based framework for domain generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 14383–14392.
- Generalizable feature learning in the presence of data bias and domain class imbalance with application to skin lesion classification. In International Conference on Medical Image Computing and Computer Assisted Intervention, 365–373. Springer.
- Mixup: Beyond empirical risk minimization. In International Conference on Learning Representations.
- Zhang, R. 2019. Making convolutional networks shift-invariant again. In International Conference on Machine Learning, 7324–7334. PMLR.
- Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition, 6277–6286.
- Random erasing data augmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, 13001–13008.
- Domain Generalization with MixStyle. In International Conference on Learning Representations.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.