Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
arXiv:2003.10780
Abstract
Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes. We analyze this mismatch from a domain adaptation point of view. First of all, we connect existing class-balanced methods for long-tailed classification to target shift, a well-studied scenario in domain adaptation. The connection reveals that these methods implicitly assume that the training data and test data share the same class-conditioned distribution, which does not hold in general and especially for the tail classes. While a head class could contain abundant and diverse training examples that well represent the expected data at inference time, the tail classes are often short of representative training data. To this end, we propose to augment the classic class-balanced learning by explicitly estimating the differences between the class-conditioned distributions with a meta-learning approach. We validate our approach with six benchmark datasets and three loss functions.
arXiv commentAccepted for publication at CVPR2020
References in corpus (10)
- SMOTE: Synthetic Minority Over-sampling Technique
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Deep Residual Learning for Image Recognition
- Unsupervised Domain Adaptation by Backpropagation
- Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
- Learning to Reweight Examples for Robust Deep Learning
- Decoupling Representation and Classifier for Long-Tailed Recognition
- Class-Balanced Loss Based on Effective Number of Samples
- Max-margin Class Imbalanced Learning with Gaussian Affinity
- Class Rectification Hard Mining for Imbalanced Deep Learning