A Robust Learning Approach to Domain Adaptive Object Detection
This addresses domain adaptation for object detection in applications like self-driving cars and surveillance, where training data is limited, but it is incremental as it builds on existing robust learning methods.
The paper tackles domain shift in object detection by framing it as a noisy label problem, proposing a robust learning framework that improves state-of-the-art accuracy on datasets like SIM10K, Cityscapes, and KITTI.
Domain shift is unavoidable in real-world applications of object detection. For example, in self-driving cars, the target domain consists of unconstrained road environments which cannot all possibly be observed in training data. Similarly, in surveillance applications sufficiently representative training data may be lacking due to privacy regulations. In this paper, we address the domain adaptation problem from the perspective of robust learning and show that the problem may be formulated as training with noisy labels. We propose a robust object detection framework that is resilient to noise in bounding box class labels, locations and size annotations. To adapt to the domain shift, the model is trained on the target domain using a set of noisy object bounding boxes that are obtained by a detection model trained only in the source domain. We evaluate the accuracy of our approach in various source/target domain pairs and demonstrate that the model significantly improves the state-of-the-art on multiple domain adaptation scenarios on the SIM10K, Cityscapes and KITTI datasets.