Our paper of Visual Intelligence (VI) Lab is accepted to International Conference on Machine Learning (ICML) 2023, which is one of the Top Conference in AI

Title: 

Scaling of Class-wise Training Losses for Post-hoc Calibration

Authors:

Seungjin Jung, Seungmo Seo, Yonghyun Jeong, Jongwon Choi

Abstract: 

The class-wise training losses often diverge as a result of the various levels of intra-class and inter-class appearance variation, and we find that the diverging class-wise training losses cause the uncalibrated prediction with its reliability. To resolve the issue, we propose a new calibration method to synchronize the class-wise training losses. We design a new training loss to alleviate the variance of class-wise training losses by using multiple class-wise scaling factors. Since our framework can compensate the training losses of overfitted classes with those of under-fitted classes, the integrated training loss is preserved, preventing the performance drop even after the model calibration. Furthermore, our method can be easily employed in the post-hoc calibration methods, allowing us to use the pre-trained model as an initial model and reduce the additional computation for model calibration. We validate the proposed framework by employing it in the various post-hoc calibration methods, which generally improves calibration performance while preserving accuracy. We also discover through the investigation that our approach performs well with unbalanced datasets and untuned hyperparameters.