Y Gong, G Mori, F Tung - arXiv preprint arXiv:2205.15236, 2022 - arxiv.org
Data imbalance, in which a plurality of the data samples come from a small proportion of labels, poses a challenge in training deep neural networks. Unlike classification, in …
Z Xu, R Liu, S Yang, Z Chai… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
The real-world data tends to be heavily imbalanced and severely skew the data-driven deep neural networks, which makes Long-Tailed Recognition (LTR) a massive challenging task …
J Noh, H Park, J Lee, B Ham - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Network calibration aims to accurately estimate the level of confidences, which is particularly important for employing deep neural networks in real-world systems. Recent approaches …
Many real-world recognition problems are characterized by long-tailed label distributions. These distributions make representation learning highly challenging due to limited …
Long-tailed visual recognition has received increasing attention in recent years. Due to the extremely imbalanced data distribution in long-tailed learning, the learning process shows …
Multimodal machine learning has achieved remarkable progress in a wide range of scenarios. However, the reliability of multimodal learning remains largely unexplored. In this …
J Chen, B Su - Proceedings of the IEEE/CVF conference on …, 2023 - openaccess.thecvf.com
How to estimate the uncertainty of a given model is a crucial problem. Current calibration techniques treat different classes equally and thus implicitly assume that the distribution of …
Real-world data typically follows a long-tailed distribution. When a small sample of tail classes does not cover the underlying distribution well, methods such as class re-balancing …
Q Gui, H Zhou, N Guo, B Niu - Machine Learning, 2024 - Springer
Semi-supervised learning (SSL) can substantially improve the performance of deep neural networks by utilizing unlabeled data when labeled data is scarce. The state-of-the-art …