Object frequency in the real world often follows a power law, leading to a mismatch between
datasets with long-tailed class distributions seen by a machine learning model and our …

We address the overlooked unbiasedness in existing long-tailed classification methods: we
find that their overall improvement is mostly attributed to the biased preference of" tail" over" …

Recently, computer vision foundation models such as CLIP and ALI-GN, have shown
impressive generalization capabilities on various downstream tasks. But their abilities to …

For long-tailed classification tasks, most works often pretrain a big model on a large-scale
(unlabeled) dataset, and then fine-tune the whole pretrained model for adapting to long …

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 …

Deep models trained on long-tailed datasets exhibit unsatisfactory performance on tail
classes. Existing methods usually modify the classification loss to increase the learning …

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 …

Self-supervised learning has achieved a great success in the representation learning of
visual and textual data. However, the current methods are mainly validated on the well …

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 this paper, we propose the Generalized Parametric Contrastive Learning (GPaCo/PaCo)
which works well on both imbalanced and balanced data. Based on theoretical analysis, we …