# VCL Challenges 2023 at ICCV 2023 Technical Report: Bi-level Adaptation Method for Test-time Adaptive Object Detection

Source: [VCL Challenges 2023 at ICCV 2023 Technical Report: Bi-level Adaptation Method for Test-time Adaptive Object Detection](<https://www.sota2.com/research/paper/68fa70d51e209131cea4d7f4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:51:52.116Z

Authors: Chenyu Lin, Yusheng He, Zhengqing Zang, Chenwei Tang, Tao Wang, Jiancheng Lv

Published: 2023-10-13T10:06:39.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2310.08986>)

[PDF](<https://arxiv.org/pdf/2310.08986.pdf>)
