2020/03/24 by Muhammad Abdullah Jamal, Jamal, Muhammad Abdullah, Matthew A. Brown +7 · 3 citations
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications #Neonatal and fetal brain pathology
paper · pdf · doi:10.48550/arxiv.2003.10780
openalex publication_date 2020/03/24 · openalex created_date 2020/04/03 · openalex updated_date 2026/07/28
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.