Year: 2025
Type: conference-paper
Abstract: Domain adaptive object detection (DAOD) aims to generalize an object detector trained on labeled source-domain data to a target domain without annotations, the core principle of which is source-target feature alignment. Typically, existing approaches employ adversarial learning to align the distributions of the source and target domains as a whole, barely considering the varying significance of distinct regions, say instances under different circumstances and foreground vs background areas, during feature alignment. To overcome the shortcoming, we investigate a differential feature alignment strategy. Specifically, a prediction-discrepancy feedback instance alignment module (dubbed PDFA) is designed to adaptively assign higher weights to instances of higher teacher-student detection discrepancy, effectively handling heavier domain-specific information. Additionally, an uncertainty-based foreground-oriented image alignment module (UFOA) is proposed to explicitly guide the model to focus more on regions of interest. Extensive experiments on widely-used DAOD datasets together with ablation studies are conducted to demonstrate the efficacy of our proposed method and reveal its superiority over other SOTA alternatives.
Authors: Xinyu He, Xinhui Li, Xiaojie Guo
Institution: Tianjin University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
Awards: G1791856828, G5946385217
OpenAlex ID: W4409364303