# Differential Alignment for Domain Adaptive Object Detection

Source: [Differential Alignment for Domain Adaptive Object Detection](<https://www.sota2.com/research/paper/68fa76361e209131cea6bdcb>)

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

Data updated: 2025-10-28T13:57:11.898Z

Authors: Xinyu He, Xinhui Li, Xiaojie Guo (1) \_\_INSTITUTION\_3\_\_ College of Intelligence, Computing, Tianjin University, Tianjin, China)

Published: 2024-12-17T11:52:10.000Z

## 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 \\emph{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 \\emph{vs} background areas, during feature alignment. To overcome the shortcoming, we investigates 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. Our code is available at https://github.com/EstrellaXyu/Differential-Alignment-for-DAOD.

## 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/2412.12830>)

[PDF](<https://arxiv.org/pdf/2412.12830.pdf>)