Asymptotic Midpoint Mixup for Margin Balancing and Moderate Broadening

TL;DR

This paper introduces asymptotic midpoint mixup, a feature augmentation technique that balances class margins and moderates margin broadening, improving representation learning in various tasks.

Contribution

The paper proposes a novel mixup variant that gradually interpolates features toward class midpoints, addressing intra- and inter-class collapse in representation learning.

Findings

Outperforms existing augmentation methods in transfer learning and imbalanced datasets.

Effectively balances class margins and moderates margin broadening.

Visual analyses confirm improved feature alignment and uniformity.

Abstract

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.