Mixup-Inference-in-Training

(★ 17)

This 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.

Mixup-Inference-in-Training 최신버젼 다운로드

최종 버전 다운로드 (.zip)
// repository documentation