The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem. Existing solutions …
S Ahn, J Ko, SY Yun - arXiv preprint arXiv:2302.05499, 2023 - arxiv.org
Class imbalance problems frequently occur in real-world tasks, and conventional deep learning algorithms are well known for performance degradation on imbalanced training …
Many real-world recognition problems are characterized by long-tailed label distributions. These distributions make representation learning highly challenging due to limited …
It's widely acknowledged that deep learning models with flatter minima in its loss landscape tend to generalize better. However, such property is under-explored in deep long-tailed …
T Ma, S Geng, M Wang, J Shao, J Lu, H Li… - arXiv preprint arXiv …, 2021 - arxiv.org
The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Existing approaches either perform class re …
Real-world data often exhibits long tail distributions with heavy class imbalance, where the majority classes can dominate the training process and alter the decision boundaries of the …
Z Zhong, J Cui, S Liu, J Jia - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Deep neural networks may perform poorly when training datasets are heavily class- imbalanced. Recently, two-stage methods decouple representation learning and classifier …
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 …
Y Zhang, XS Wei, B Zhou, J Wu - … of the AAAI conference on artificial …, 2021 - ojs.aaai.org
In recent years, visual recognition on challenging long-tailed distributions, where classes often exhibit extremely imbalanced frequencies, has made great progress mostly based on …