B Zhu, Y Niu, XS Hua, H Zhang - … of the AAAI conference on artificial …, 2022 - ojs.aaai.org
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 …
P Chu, X Bian, S Liu, H Ling - … Conference, Glasgow, UK, August 23–28 …, 2020 - Springer
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 …
S Zhang, C Chen, X Hu, S Peng - Neurocomputing, 2023 - Elsevier
Deep models trained on long-tailed datasets exhibit unsatisfactory performance on tail classes. Existing methods usually modify the classification loss to increase the learning …
H Wei, L Tao, R Xie, L Feng… - … Conference on Machine …, 2022 - proceedings.mlr.press
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 …
J Cui, Z Zhong, S Liu, B Yu… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
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 …