IMWA: Iterative Model Weight Averaging Benefits Class-Imbalanced Learning Tasks

arXiv:2404.16331v1 Announce Type: new
Abstract: Model Weight Averaging (MWA) is a technique that seeks to enhance model's performance by averaging the weights of multiple trained models. This paper first empirically finds that 1) the vanilla MWA can benefit the class-imbalanced learning, and 2) performing model averaging in the early epochs of training yields a greater performance improvement than doing that in later epochs. Inspired by these two observations, in this paper we propose a novel MWA technique for class-imbalanced learning …

abstract arxiv benefit benefits class cs.ai cs.cv iterative multiple paper performance s performance tasks type