dengbaowang / Mixup-Inference-in-Training

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.
16Updated last year

Alternatives and similar repositories for Mixup-Inference-in-Training:

Users that are interested in Mixup-Inference-in-Training are comparing it to the libraries listed below