特征(语言学)
计算机科学
人工智能
模式识别(心理学)
特征向量
一般化
特征学习
机器学习
特征提取
规范(哲学)
数学
政治学
语言学
数学分析
哲学
法学
作者
Mengke Li,Yiu‐ming Cheung,Juyong Jiang
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2022-07-18
卷期号:: 1-6
被引量:20
标识
DOI:10.1109/icme52920.2022.9860003
摘要
Deep neural networks frequently suffer from performance degradation when the training data is long-tailed because several majority classes dominate the training, resulting in a biased model. Recent studies have made a great effort in solving this issue by obtaining good representations from data space, but few of them pay attention to the influence of feature norm on the predicted results. In this paper, we therefore address the long-tailed problem from feature space and thereby propose the feature-balanced loss. Specifically, we encourage larger feature norms of tail classes by giving them relatively stronger stimuli. Moreover, the stimuli intensity is gradually increased in the way of curriculum learning, which improves the generalization of the tail classes, meanwhile maintaining the performance of the head classes. Extensive experiments on multiple popular long-tailed recognition benchmarks demonstrate that the feature-balanced loss achieves superior performance gains compared with the state-of-the-art methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI