With the rapid increase of large-scale, real-world datasets, it becomes critical to address the
problem of long-tailed data distribution (ie, a few classes account for most of the data, while …

Real-world data often follow a long-tailed distribution as the frequency of each class is
typically different. For example, a dataset can have a large number of under-represented …

Large-scale data from real-world usually follow a long-tailed distribution (ie, a few majority
classes occupy plentiful training data, while most minority classes have few samples) …

Training process is crucial for the deployment of the network in applications which have two
strict requirements on both accuracy and robustness. However, most existing approaches …

Imbalanced datasets widely exist in practice and are a great challenge for training deep
neural models with a good generalization on infrequent classes. In this work, we propose a …

Maximizing the separation between classes constitutes a well-known inductive bias in
machine learning and a pillar of many traditional algorithms. By default, deep networks are …

Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-
imbalance but the testing criterion requires good generalization on less frequent classes …

Recent success in deep learning has partially been driven by training increasingly
overparametrized networks on ever larger datasets. It is therefore natural to ask: how much …

Deep image classifiers often perform poorly when training data are heavily class-
imbalanced. In this work, we propose a new regularization technique, Remix, that relaxes …

Deep neural networks usually perform poorly when the training dataset suffers from extreme
class imbalance. Recent studies found that directly training with out-of-distribution data (ie …