A Pairwise DomMix Attentive Adversarial Network for Unsupervised Domain Adaptive Object Detection
This work addresses domain adaptation for object detection in computer vision, offering an incremental improvement over existing methods.
The paper tackles the problem of unidirectional domain transfer in unsupervised domain adaptive object detection, which can lead to suboptimal adaptation under large domain shifts, by proposing a pairwise attentive adversarial network with a Domain Mixup module that achieves superior performance on benchmark datasets.
Unsupervised Domain Adaptive Object Detection (DAOD) could adapt a model trained on a source domain to an unlabeled target domain for object detection. Existing unsupervised DAOD methods usually perform feature alignments from the target to the source. Unidirectional domain transfer would omit information about the target samples and result in suboptimal adaptation when there are large domain shifts. Therefore, we propose a pairwise attentive adversarial network with a Domain Mixup (DomMix) module to mitigate the aforementioned challenges. Specifically, a deep-level mixup is employed to construct an intermediate domain that allows features from both domains to share their differences. Then a pairwise attentive adversarial network is applied with attentive encoding on both image-level and instance-level features at different scales and optimizes domain alignment by adversarial learning. This allows the network to focus on regions with disparate contextual information and learn their similarities between different domains. Extensive experiments are conducted on several benchmark datasets, demonstrating the superiority of our proposed method.