1 code implementation • NeurIPS 2021 • Hyuck Lee, Seungjae Shin, Heeyoung Kim
The ABC is trained with a class-balanced loss of a minibatch, while using high-quality representations learned from all data points in the minibatch using the backbone SSL algorithm to avoid overfitting and information loss. Moreover, we use consistency regularization, a recent SSL technique for utilizing unlabeled data in a modified way, to train the ABC to be balanced among the classes by selecting unlabeled data with the same probability for each class.
1 code implementation • 15 Mar 2024 • Hyuck Lee, Heeyoung Kim
Pseudo-label-based semi-supervised learning (SSL) algorithms trained on a class-imbalanced set face two cascading challenges: 1) Classifiers tend to be biased towards majority classes, and 2) Biased pseudo-labels are used for training.
1 code implementation • NeurIPS 2021 • keunseo kim, JunCheol Shin, Heeyoung Kim
Several out-of-distribution (OOD) detection scores have been recently proposed for deep generative models because the direct use of the likelihood threshold for OOD detection has been shown to be problematic.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • NeurIPS 2020 • Taewon Jeong, Heeyoung Kim
The joint analysis of N sub-tasks facilitates simultaneous classification and OOD detection and, furthermore, offers an advantage, in that it does not require re-training when the number of classes for a test task differs from that for training tasks; it is sufficient to simply assume as many sub-tasks as the number of classes for the test task.