罗伊特
计量经济学
逻辑回归
统计
经济
数学
计算机科学
作者
Aditya Krishna Menon,Sadeep Jayasumana,Ankit Singh Rawat,Himanshu Jain,Andreas Veit,Sanjiv Kumar
出处
期刊:Cornell University - arXiv
日期:2020-01-01
被引量:143
标识
DOI:10.48550/arxiv.2007.07314
摘要
Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels are associated with only a few samples. This poses a challenge for generalisation on such labels, and also makes naïve learning biased towards dominant labels. In this paper, we present two simple modifications of standard softmax cross-entropy training to cope with these challenges. Our techniques revisit the classic idea of logit adjustment based on the label frequencies, either applied post-hoc to a trained model, or enforced in the loss during training. Such adjustment encourages a large relative margin between logits of rare versus dominant labels. These techniques unify and generalise several recent proposals in the literature, while possessing firmer statistical grounding and empirical performance.
科研通智能强力驱动
Strongly Powered by AbleSci AI