通过剪枝辅助的域特定权重调制实现持续域自适应
Continual Domain Adaptation through Pruning-aided Domain-specific Weight Modulation
AI总结:
本文提出一种结合剪枝与域特定权重调制的持续域自适应方法,通过保留域特定特征和基于批归一化的推理策略,在持续学习场景下实现最先进性能并显著缓解灾难性遗忘。
摘要:
在本文中,我们提出在持续学习(CL)的实际场景下解决无监督域自适应(UDA)问题的方法。目标是在持续变化的域上更新模型,同时保留域特定知识,以防止对过去已见域的灾难性遗忘。为此,我们构建了一个利用模型固有容量并通过剪枝来保留域特定特征的框架。我们还使用一种新颖的基于批归一化的度量进行有效推理,以准确预测最终要使用的模型参数。我们的方法不仅取得了最先进的性能,而且显著防止了对过去域的灾难性遗忘。我们的代码已公开发布。
英文摘要:
In this paper, we propose to develop a method to address unsupervised domain adaptation (UDA) in a practical setting of continual learning (CL). The goal is to update the model on continually changing domains while preserving domain-specific knowledge to prevent catastrophic forgetting of past-seen domains. To this end, we build a framework for preserving domain-specific features utilizing the inherent model capacity via pruning. We also perform effective inference using a novel batch-norm based metric to predict the final model parameters to be used accurately. Our approach achieves not only state-of-the-art performance but also prevents catastrophic forgetting of past domains significantly. Our code is made publicly available.
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。