Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection
It addresses the challenge of unsupervised cross-domain object detection, which is important for applications like autonomous driving where labeled data is scarce, but the method appears incremental as it builds on existing adaptation techniques.
This work tackles the problem of generalizing a pre-trained object detector to a new target domain without labels, achieving state-of-the-art performance on multiple cross-domain object detection benchmarks.
This work tackles the unsupervised cross-domain object detection problem which aims to generalize a pre-trained object detector to a new target domain without labels. We propose an uncertainty-aware model adaptation method, which is based on two motivations: 1) the estimation and exploitation of model uncertainty in a new domain is critical for reliable domain adaptation; and 2) the joint alignment of distributions for inputs (feature alignment) and outputs (self-training) is needed. To this end, we compose a Bayesian CNN-based framework for uncertainty estimation in object detection, and propose an algorithm for generation of uncertainty-aware pseudo-labels. We also devise a scheme for joint feature alignment and self-training of the object detection model with uncertainty-aware pseudo-labels. Experiments on multiple cross-domain object detection benchmarks show that our proposed method achieves state-of-the-art performance.