Deep learning has achieved remarkable success in numerous domains with help from large
amounts of big data. However, the quality of data labels is a concern because of the lack of …

Supervised training of deep learning models requires large labeled datasets. There is a
growing interest in obtaining such datasets for medical image analysis applications …

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 …

Unsupervised person re-identification (re-ID) aims at learning discriminative representations
for person retrieval from unlabeled data. Recent techniques accomplish this task by using …

Deep networks have strong capacities of embedding data into latent representations and
finishing following tasks. However, the capacities largely come from high-quality annotated …

In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed
recognition. Based on theoretical analysis, we observe supervised contrastive loss tends to …

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 …

As the class size grows, maintaining a balanced dataset across many classes is challenging
because the data are long-tailed in nature; it is even impossible when the sample-of-interest …

Deep classifiers have achieved great success in visual recognition. However, real-world
data is long-tailed by nature, leading to the mismatch between training and testing …

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …