Multi-Scale Adversarial Cross-Domain Detection with Robust Discriminative Learning

Youngsun Pan, Andy J. Ma, Yuan Gao, Jinpeng Wang, Yiqi Lin

Abstract: Domain shift practically exists in almost all computer vision tasks including object detection, caused by which the performance drops evidently. Most existing methods for domain adaptation are specially designed for classification. For object detection, existing methods separate domain shift into image-level shift and instance-level shift and align image-level feature and instance-level feature respectively. However, we find that there are two problems which remain unsolved yet. First, the scale of objects is not the same even in an image. Second, negative transfer can affect model performance if not handled properly. We improve the performance of cross-domain detection from three perspectives: 1) using multiple dilated convolution kernels with different dilation rate to reduce the image-level domain discrepancy; 2) removing images or instances with low transferability to weaken the influence of negative transfer; 3) diversifying distributions by keeping instances' feature away from each other, and then pull them closer to the center of each category, so that make source samples distribution more dispersed and more robust for cross-domain detection. We test our model with Cityscapes [5], Foggy Cityscape [30] and SIM 10K [18] datasets, experimental results show that our method outperforms the state-of-the-art for object detection under the setting of unsupervised domain adaptation (UDA).