Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective

TL;DR

This paper introduces a learnable embedding augmentation method that expands tail class distributions in deep feature space, improving discrimination in long-tailed data scenarios like face recognition and person re-identification.

Contribution

It proposes a novel feature cloud construction technique to enhance tail class diversity and mitigate feature space distortion in long-tailed learning.

Findings

Improved recognition accuracy on long-tailed datasets

Enhanced intra-class diversity for tail classes

Effective in face recognition and person re-identification

Abstract

This paper considers learning deep features from long-tailed data. We observe that in the deep feature space, the head classes and the tail classes present different distribution patterns. The head classes have a relatively large spatial span, while the tail classes have significantly small spatial span, due to the lack of intra-class diversity. This uneven distribution between head and tail classes distorts the overall feature space, which compromises the discriminative ability of the learned features. Intuitively, we seek to expand the distribution of the tail classes by transferring from the head classes, so as to alleviate the distortion of the feature space. To this end, we propose to construct each feature into a "feature cloud". If a sample belongs to a tail class, the corresponding feature cloud will have relatively large distribution range, in compensation to its lack of diversity. It allows each tail sample to push the samples from other classes far away, recovering the intra-class diversity of tail classes. Extensive experimental evaluations on person re-identification and face recognition tasks confirm the effectiveness of our method.