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

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.

References in corpus (8)

• SMOTE: Synthetic Minority Over-sampling Technique
• A systematic study of the class imbalance problem in convolutional neural networks
• A Discriminatively Learned CNN Embedding for Person Re-identification
• NormFace: L2 Hypersphere Embedding for Face Verification
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• L2-constrained Softmax Loss for Discriminative Face Verification
• Gradient Harmonized Single-stage Detector
• Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification

Cited by in corpus (9)

• Free Lunch for Few-shot Learning: Distribution Calibration
• Static Inference Meets Deep Learning: A Hybrid Type Inference Approach for Python
• Feature Fusion from Head to Tail for Long-Tailed Visual Recognition
• CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning
• MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
• Distributional Robustness Loss for Long-tail Learning
• Graph Classification by Mixture of Diverse Experts
• Inter-intra Variant Dual Representations forSelf-supervised Video Recognition
• A Linkage-based Doubly Imbalanced Graph Learning Framework for Face Clustering