Real-world classification problems typically exhibit an imbalanced or long-tailed label
distribution, wherein many labels are associated with only a few samples. This poses a …

Long-tailed learning has attracted much attention recently, with the goal of improving
generalisation for tail classes. Most existing works use supervised learning without …

Unlike the case when using a balanced training dataset, the per-class recall (ie, accuracy) of
neural networks trained with an imbalanced dataset are known to vary a lot from category to …

Many real-world recognition problems are characterized by long-tailed label distributions.
These distributions make representation learning highly challenging due to limited …

Real-world data usually couples the label ambiguity and heavy imbalance, challenging the
algorithmic robustness of partial label learning (PLL) and long-tailed learning (LT). The …

Real-world data universally confronts a severe class-imbalance problem and exhibits a long-
tailed distribution, ie, most labels are associated with limited instances. The naïve models …

Learning with Noisy Labels (LNL) has become an appealing topic, as imperfectly annotated
data are relatively cheaper to obtain. Recent state-of-the-art approaches employ specific …

The memorization effects of deep networks show that they will first memorize training data
with clean labels and then those with noisy labels. The early stopping method therefore can …

Classical machine learning implicitly assumes that labels of the training data are sampled
from a clean distribution, which can be too restrictive for real-world scenarios. However …

In learning with noisy labels, the sample selection approach is very popular, which regards
small-loss data as correctly labeled during training. However, losses are generated on-the …