论文标题

简单:简单域的概括基线,没有铃铛和哨子

SimpleDG: Simple Domain Generalization Baseline without Bells and Whistles

论文作者

Lv, Zhi, Lin, Bo, Liang, Siyuan, Wang, Lihua, Yu, Mochen, Tang, Yao, Liang, Jiajun

论文摘要

我们提出了一个简单的领域概括基线,该基线在2022年Nico Challenge挑战赛中分别赢得了共同环境概括和混合上下文概括曲目的第二名。我们验证了最近的文献中的创建,域,ERM与最近的最新领域通用方法相比,是一个强大的基线,并且与其他简单的简单范围的简单方法相比,包括几个简单但有效的概括性。代码可从https://github.com/megvii-research/simpledg获得

We present a simple domain generalization baseline, which wins second place in both the common context generalization track and the hybrid context generalization track respectively in NICO CHALLENGE 2022. We verify the founding in recent literature, domainbed, that ERM is a strong baseline compared to recent state-of-the-art domain generalization methods and propose SimpleDG which includes several simple yet effective designs that further boost generalization performance. Code is available at https://github.com/megvii-research/SimpleDG

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源