A recent study has shown a phenomenon called neural collapse in that the within-class
means of features and the classifier weight vectors converge to the vertices of a simplex …

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) …

In this paper, our goal is to design a simple learning paradigm for long-tail visual
recognition, which not only improves the robustness of the feature extractor but also …

In this work we present DREAM, an fMRI-to-image method for reconstructing viewed images
from brain activities, grounded on fundamental knowledge of the human visual system. We …

Long-tail learning has received significant attention in recent years due to the challenge it
poses with extremely imbalanced datasets. In these datasets, only a few classes (known as …

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 …

Real-world datasets exhibit imbalances of varying types and degrees. Several techniques
based on re-weighting and margin adjustment of loss are often used to enhance the …

Deep neural networks have made huge progress in the last few decades. However, as the
real-world data often exhibits a long-tailed distribution, vanilla deep models tend to be …

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 …

Learning high-quality representation is important and essential for visual recognition.
Unfortunately, traditional representation learning suffers from fairness issues since the …