IMWA：迭代模型权重平均助力类别不平衡学习任务
IMWA: Iterative Model Weight Averaging Benefits Class-Imbalanced Learning Tasks
AI总结：
针对类别不平衡学习任务，本文提出迭代模型权重平均（IMWA）技术，将训练划分为多片段，每个片段内训练并平均模型权重，在相同计算成本下提升性能，且可增强EMA策略方法的性能。
摘要：
模型权重平均（MWA）是通过平均多个训练模型权重来提升模型性能的技术。本文首先通过实证发现：1）普通MWA可助力类别不平衡学习；2）在训练早期epoch进行模型平均比后期epoch带来更大性能提升。受这两个观察启发，本文提出一种适用于类别不平衡学习任务的新型MWA技术——迭代模型权重平均（IMWA）。具体而言，IMWA将整个训练阶段划分为多个片段，每个片段内从同一初始权重训练多个模型并平均，该平均权重作为下一片段的初始权重。相比普通MWA，IMWA在相同计算成本下性能提升更显著，且能进一步增强采用EMA策略方法的性能。
英文摘要：
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 tasks named Iterative Model Weight Averaging (IMWA). Specifically, IMWA divides the entire training stage into multiple episodes. Within each episode, multiple models are concurrently trained from the same initialized model weight, and subsequently averaged into a singular model. Then, the weight of this average model serves as a fresh initialization for the ensuing episode, thus establishing an iterative learning paradigm. Compared to vanilla MWA, IMWA achieves higher performance improvements with the same computational cost. Moreover, IMWA can further enhance the performance of those methods employing EMA strategy, demonstrating that IMWA and EMA can complement each other. Extensive experiments on various class-imbalanced learning tasks, i.e., class-imbalanced image classification, semi-supervised class-imbalanced image classification and semi-supervised object detection tasks showcase the effectiveness of our IMWA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
