To address the challenges of long-tailed classification, researchers have proposed several
approaches to reduce model bias, most of which assume that classes with few samples are …

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 …

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 …

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 …

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 …

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 …