no code implementations • 21 Jul 2022 • Jun Ho Lee, Jae Soon Baik, Tae Hwan Hwang, Jun Won Choi
By combining the aforementioned metrics, we present the proposed {\it self-ensemble-based robust training} (SRT) method, which can filter the samples with noisy labels to reduce their influence on training.
no code implementations • 5 Jul 2022 • Jae Soon Baik, In Young Yoon, Jun Won Choi
The student models are given a fixed number of temporal self-ensemble models, and the teacher model is constructed by averaging the weights of the student models.
no code implementations • 5 Jul 2022 • Jae Soon Baik, In Young Yoon, Jun Won Choi
There is growing interest in the challenging visual perception task of learning from long-tailed class distributions.