Wasserstein Distance Based Domain Adaptation for Object Detection
This addresses domain shift problems in object detection for computer vision applications, representing an incremental improvement over prior adversarial training methods.
The paper tackles domain adaptation for object detection by minimizing Wasserstein distance instead of cross entropy or Jensen-Shannon divergence to improve stability in high-dimensional feature spaces, and shows improved target domain performance empirically.
In this paper, we present an adversarial unsupervised domain adaptation framework for object detection. Prior approaches utilize adversarial training based on cross entropy between the source and target domain distributions to learn a shared feature mapping that minimizes the domain gap. Here, we minimize the Wasserstein distance between the two distributions instead of cross entropy or Jensen-Shannon divergence to improve the stability of domain adaptation in high-dimensional feature spaces that are inherent to object detection task. Additionally, we remove the exact consistency constraint of the shared feature mapping between the source and target domains, so that the target feature mapping can be optimized independently, which is necessary in the case of significant domain gap. We empirically show that the proposed framework can mitigate domain shift in different scenarios, and provide improved target domain object detection performance.