Previous unsupervised domain adaptation methods did not handle the cross-domain problem from the perspective of frequency for computer vision. The images or feature maps of different domains can be decomposed into the low-frequency component and high-frequency component. This paper proposes the assumption that low-frequency information is more domain-invariant while the high-frequency information contains domain-related information. Hence, we introduce an approach, named low-frequency module (LFM), to extract domain-invariant feature representations. The LFM is constructed with the digital Gaussian low-pass filter. Our method is easy to implement and introduces no extra hyperparameter. We design two effective ways to utilize the LFM for domain adaptation, and our method is complementary to other existing methods and formulated as a plug-and-play unit that can be combined with these methods. Experimental results demonstrate that our LFM outperforms state-of-the-art methods for various computer vision tasks, including image classification and object detection.
翻译:先前未经监督的域适应方法没有从计算机视觉的频率角度处理跨域问题。 不同域的图像或地貌地图可以分解成低频组件和高频组件。 本文提出低频信息更具域异性而高频信息包含域相关信息的假设。 因此, 我们引入了一个名为低频模块( LFM)的方法来提取域异性特征。 LFM 是用数字高斯低通道过滤器构建的。 我们的方法很容易执行, 并且没有引入额外的超光度计。 我们设计了两种有效的方法来利用 LFM 进行域适应, 我们的方法是与其他现有方法互补, 并形成一个插件和玩器, 可以与这些方法相结合。 实验结果显示我们的LFMD 超越了各种计算机视觉任务( 包括图像分类和对象探测) 的状态方法 。