Deng-Bao Wang

PhD student | Machine Learning

代表作品 / 项目

Mixup-Inference-in-Training⭐ 17This is the implementation of our CVPR'23 paper On the Pitfall of Mixup for Uncertainty Calibration. In the paper, we conduct a series of empirical studies showing the calibration issue of Mixup, and propose a new mixup training strategy to address this issue.
Rethinking-Calibration-of-Deep-Neural-Networks⭐ 16
PLP⭐ 4
CLL_POCR⭐ 4
CompLossForNoisyLabels⭐ 4

条目信息来自其公开主页与公开发布内容。按本站规范，页面不展示任何联系方式。需要更正或删除？通过收录与更正通道提交，24 小时内处理。