Single-Stage Object Detection from Top-View Grid Maps on Custom Sensor Setups
This work addresses domain adaptation for object detection in automated driving, but it is incremental as it builds on existing methods like RetinaNet.
The paper tackles the problem of training robust single-stage object detectors for top-view grid maps in automated driving using custom sensor setups, and demonstrates that their adversarial domain adaptation strategy improves detection accuracy for unlabeled domains, as evaluated on nuScenes and KITTI benchmarks.
We present our approach to unsupervised domain adaptation for single-stage object detectors on top-view grid maps in automated driving scenarios. Our goal is to train a robust object detector on grid maps generated from custom sensor data and setups. We first introduce a single-stage object detector for grid maps based on RetinaNet. We then extend our model by image- and instance-level domain classifiers at different feature pyramid levels which are trained in an adversarial manner. This allows us to train robust object detectors for unlabeled domains. We evaluate our approach quantitatively on the nuScenes and KITTI benchmarks and present qualitative domain adaptation results for unlabeled measurements recorded by our experimental vehicle. Our results demonstrate that object detection accuracy for unlabeled domains can be improved by applying our domain adaptation strategy.