대학원소개

논문성과

VI Lab's (Prof. Jongwon Choi) paper accepted to ICML 2023 (AI Top-tier Conference)

관리자 │ 2023-04-25

HIT

50728


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.



이전글 IPIS Lab's (Prof. Joonki Paik) paper published in Scientific Reports (IF: 5.516)
다음글 콘텐츠기획/정책/비즈니스 연구실(Prof. Heeyoung Cho) paper publishe...