Balanced Teacher for Source-Free Object Detection
Jinhong Deng, Wen Li, Lixin Duan
Abstract
We study a practical domain adaptation task, named source-free object detection (SFOD), which aims to adapt a pre-trained source detector to an unlabeled target domain without access to the original labeled source domain samples. In this paper, we design a new self-training approach for SFOD called Balance Teacher based on the mean teacher model. We target two key issues when using self-training for SFOD: 1) imbalanced label distribution when using pseudo-labels for supervising the model training, and 2) imbalanced image distribution, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e</i> ., significant data variance in the target domain. To address these issues, we first design a Class-balanced Instance Selection (CBIS) module to automatically balance different classes when selecting pseudo-labeled instances during the training process. Then, we propose a Progressive Target Variance Minimization (PTVM) to cope with the imbalanced image distribution in the target domain, where the feature distributions of certainty and uncertainty target samples are progressively aligned to alleviate the data distribution variance. In this way, the teacher model can provide high-quality pseudo-labels and guide the student model to adapt gradually to the target domain. We have conducted extensive experiments on five widely used benchmarks, and the experimental results clearly show the superiority of our method over the state-of-the-art baselines.