In the feature space, the collapse between features invokes critical problems in representation learning by remaining the features undistinguished. Interpolation-based augmentation methods such as mixup have shown their effectiveness in relieving the collapse problem between different classes, called inter-class collapse. However, intra-class collapse raised in coarse-to-fine transfer learning has not been discussed in the augmentation approach. To address them, we propose a better feature augmentation method, asymptotic midpoint mixup. The method generates augmented features by interpolation but gradually moves them toward the midpoint of inter-class feature pairs. As a result, the method induces two effects: 1) balancing the margin for all classes and 2) only moderately broadening the margin until it holds maximal confidence. We empirically analyze the collapse effects by measuring alignment and uniformity with visualizing representations. Then, we validate the intra-class collapse effects in coarse-to-fine transfer learning and the inter-class collapse effects in imbalanced learning on long-tailed datasets. In both tasks, our method shows better performance than other augmentation methods.

翻译：在特征空间中，特征之间的坍缩会导致表征学习中特征无法区分的关键问题。基于插值的增强方法（如混合法）已证明能有效缓解不同类别间的类间坍缩问题。然而，在粗到细的迁移学习中出现的类内坍缩问题尚未在增强方法中得到探讨。为此，我们提出一种更优的特征增强方法——渐近中点混合。该方法通过插值生成增强特征，并逐步将其移向类间特征对的中心点。最终，该方法产生两种效果：1）平衡所有类别的边界；2）仅适度拓宽边界直至达到最大置信度。我们通过可视化表征并测量对齐度与均匀性，对坍缩效应进行了实证分析。随后，我们在长尾数据集上的粗到细迁移学习中验证了类内坍缩效应，在非平衡学习中验证了类间坍缩效应。在这两项任务中，我们的方法均展现出优于其他增强方法的性能。