Animal behavior, as one of the most crucial indicators of animal health and welfare, provides
rich insights into animal physical and mental states. Automated animal activity recognition …

Industrial products typically lack defects in smart manufacturing systems, which leads to an
extremely imbalanced task of recognizing surface defects. With this imbalanced sample …

In the field of visual scene understanding, deep neural networks have made impressive
advancements in various core tasks like segmentation, tracking, and detection. However …

Current object detectors are limited in vocabulary size due to the small scale of detection
datasets. Image classifiers, on the other hand, reason about much larger vocabularies, as …

Real-world data typically follow a long-tailed distribution, where a few majority categories
occupy most of the data while most minority categories contain a limited number of samples …

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims
to train well-performing deep models from a large number of images that follow a long-tailed …

In the real open world, data tends to follow long-tailed class distributions, motivating the well-
studied long-tailed recognition (LTR) problem. Naive training produces models that are …

The heavy reliance on data is one of the major reasons that currently limit the development
of deep learning. Data quality directly dominates the effect of deep learning models, and the …

Self-supervised learning (SSL) is a scalable way to learn general visual representations
since it learns without labels. However, large-scale unlabeled datasets in the wild often have …

The networks trained on the long-tailed dataset vary remarkably, despite the same training
settings, which shows the great uncertainty in long-tailed learning. To alleviate the …