DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception
This addresses the scalability issue in BEV perception for autonomous systems by enabling learning from unlabelled data, though it appears incremental as it builds on existing domain adaptation and BEV methods.
The paper tackles the problem of unsupervised domain adaptation for camera-only Bird's Eye View perception, which is under-explored, and introduces DA-BEV, a framework that uses query-based adversarial learning and self-training to achieve superior performance across multiple datasets and tasks like 3D object detection and 3D scene segmentation.
Camera-only Bird's Eye View (BEV) has demonstrated great potential in environment perception in a 3D space. However, most existing studies were conducted under a supervised setup which cannot scale well while handling various new data. Unsupervised domain adaptive BEV, which effective learning from various unlabelled target data, is far under-explored. In this work, we design DA-BEV, the first domain adaptive camera-only BEV framework that addresses domain adaptive BEV challenges by exploiting the complementary nature of image-view features and BEV features. DA-BEV introduces the idea of query into the domain adaptation framework to derive useful information from image-view and BEV features. It consists of two query-based designs, namely, query-based adversarial learning (QAL) and query-based self-training (QST), which exploits image-view features or BEV features to regularize the adaptation of the other. Extensive experiments show that DA-BEV achieves superior domain adaptive BEV perception performance consistently across multiple datasets and tasks such as 3D object detection and 3D scene segmentation.