VCL Challenges 2023 at ICCV 2023 Technical Report: Bi-level Adaptation Method for Test-time Adaptive Object Detection
This work addresses incremental improvements in object detection for computer vision applications, focusing on domain adaptation challenges.
The paper tackled test-time adaptation for object detection by proposing a bi-level adaptation method combining image-level filters and detector-level mean teacher modules, achieving 38.3% mAP on the target domain with a minimal drop of 4.2%.
This report outlines our team's participation in VCL Challenges B Continual Test_time Adaptation, focusing on the technical details of our approach. Our primary focus is Testtime Adaptation using bi_level adaptations, encompassing image_level and detector_level adaptations. At the image level, we employ adjustable parameterbased image filters, while at the detector level, we leverage adjustable parameterbased mean teacher modules. Ultimately, through the utilization of these bi_level adaptations, we have achieved a remarkable 38.3% mAP on the target domain of the test set within VCL Challenges B. It is worth noting that the minimal drop in mAP, is mearly 4.2%, and the overall performance is 32.5% mAP.