# AIR-DA: Adversarial Image Reconstruction for Unsupervised Domain Adaptive Object Detection Source: [AIR-DA: Adversarial Image Reconstruction for Unsupervised Domain Adaptive Object Detection]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:08:40.604Z Authors: Kunyang Sun, Wei Lin, Haoqin Shi, Zhengming Zhang, Yongming Huang, Horst Bischof Published: 2023-03-27T16:51:51.000Z ## Abstract Unsupervised domain adaptive object detection is a challenging vision task where object detectors are adapted from a label-rich source domain to an unlabeled target domain. Recent advances prove the efficacy of the adversarial based domain alignment where the adversarial training between the feature extractor and domain discriminator results in domain-invariance in the feature space. However, due to the domain shift, domain discrimination, especially on low-level features, is an easy task. This results in an imbalance of the adversarial training between the domain discriminator and the feature extractor. In this work, we achieve a better domain alignment by introducing an auxiliary regularization task to improve the training balance. Specifically, we propose Adversarial Image Reconstruction (AIR) as the regularizer to facilitate the adversarial training of the feature extractor. We further design a multi-level feature alignment module to enhance the adaptation performance. Our evaluations across several datasets of challenging domain shifts demonstrate that the proposed method outperforms all previous methods, of both one- and two-stage, in most settings. ## 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]() [PDF]()