Despite significant advances in deep learning, models often struggle to generalize well to new, unseen domains, especially when training data is limited. To address this challenge, we propose a novel approach for distribution-aware latent augmentation that leverages the relationships across samples to guide the augmentation procedure. Our approach first degrades the samples stochastically in the latent space, mapping them to augmented labels, and then restores the samples from their corrupted versions during training. This process confuses the classifier in the degradation step and restores the overall class distribution of the original samples, promoting diverse intra-class/cross-domain variability. We extensively evaluate our approach on a diverse set of datasets and tasks, including domain generalization benchmarks and medical imaging datasets with strong domain shift, where we show our approach achieves significant improvements over existing methods for latent space augmentation. We further show that our method can be flexibly adapted to long-tail recognition tasks, demonstrating its versatility in building more generalizable models. Code is available at https://github.com/nerdslab/LatentDR.

翻译：尽管深度学习取得了显著进展，但模型在面对未见过的全新领域时仍难以实现良好的泛化，尤其是在训练数据有限的情况下。为解决这一挑战，我们提出了一种新颖的分布感知潜在空间增强方法，该方法利用样本间的关联关系来指导增强过程。我们的方法首先在潜在空间中对样本进行随机退化，将其映射到增强后的标签分布，随后在训练过程中从受扰动的版本中恢复样本。这一过程在退化步骤中混淆了分类器，并恢复了原始样本的整体类别分布，从而促进了类内/跨域多样性。我们在多样化的数据集和任务上广泛评估了该方法，包括领域泛化基准测试以及具有强领域偏移的医学影像数据集，实验结果表明，我们的方法在潜在空间增强方面相较于现有方法取得了显著提升。此外，我们进一步证明了该方法可灵活适应长尾识别任务，展现了其在构建更具泛化能力模型方面的通用性。代码已开源至 https://github.com/nerdslab/LatentDR。