Asynchronous Modeling: A Dual-phase Perspective for Long-Tailed Recognition

Hu Zhang, Linchao Zhu, Yi Yang

Keywords: long-tailed classification, gradient distortion, asynchronous modeling

Abstract: This work explores deep learning based classification model on real-world datasets with a long-tailed distribution. Most of previous works deal with the long-tailed classification problem by re-balancing the overall distribution within the whole dataset or directly transferring knowledge from data-rich classes to data-poor ones. In this work, we consider the gradient distortion in long-tailed classification when the gradient on data-rich classes and data-poor ones are incorporated simultaneously, i.e., shifted gradient direction towards data-rich classes as well as the enlarged variance by the gradient fluctuation on data-poor classes. Motivated by such phenomenon, we propose to disentangle the distinctive effects of data-rich and data-poor gradient and asynchronously train a model via a dual-phase learning process. The first phase only concerns the data-rich classes. In the second phase, besides the standard classification upon data-poor classes, we propose an exemplar memory bank to reserve representative examples and a memory-retentive loss via graph matching to retain the relation between two phases. The extensive experimental results on four commonly used long-tailed benchmarks including CIFAR100-LT, Places-LT, ImageNet-LT and iNaturalist 2018 highlight the excellent performance of our proposed method.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=ZqloVI9kWB