Domain Adaptive Object Detection via Balancing between Self-Training and Adversarial Learning

Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz, Mohsen Ali

Abstract:

Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and
background. Most current methods align domains by using image or instance-level adversarial feature alignment. This often suffers due to
unwanted background and lacks class-specific alignment. A straightforward approach to promote class-level alignment is to use high
confidence predictions on unlabeled domain as pseudo-labels. These predictions are often noisy since model is poorly calibrated under
domain shift. In this paper, we propose to leverage model’s predictive uncertainty to strike the right balance between adversarial feature
alignment and class-level alignment. We develop a technique to quantify predictive uncertainty on class assignments and bounding-box
predictions. Model predictions with low uncertainty are used to generate pseudo-labels for self-training, whereas the ones with higher
uncertainty are used to generate tiles for adversarial feature alignment. This synergy between tiling around uncertain object regions and
generating pseudo-labels from highly certain object regions allows capturing both image and instance-level context during the model
adaptation. We report thorough ablation study to reveal the impact of different components in our approach. Results on five diverse and
challenging adaptation scenarios show that our approach outperforms existing state-of-the-art methods with noticeable margins