Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

By Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Aréchiga, Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, Bingyi Kang, Saining Xie and 9 more. 2020

Citations in the corpus

• Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation (2020, neutral): “, meta-learning [63, 29, 32], causal inference [58], Bayesian methods [34], etc.”
• CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning (2021, unknown): “Similar observations are made on other SSL algorithms, and also on fully-supervised class-imbalanced learning [19].”