# Towards Online Domain Adaptive Object Detection

arXiv: https://arxiv.org/abs/2204.05289 · HTML: https://mlsanity.com/paper/2204.05289/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 71 references that are in the map.
- First posted on arXiv 11 Apr 2022.

## Builds on (most cited first, 30 of 57)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [High-Resolution Representations for Labeling Pixels and Regions](https://mlsanity.com/paper/1904.04514/) (2019)

## Built on by (most cited first, 30 of 36)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Contrastive Mean Teacher for Domain Adaptive Object Detectors](https://mlsanity.com/paper/2305.03034/) (2023)
- [ActMAD: Activation Matching to Align Distributions for Test-Time-Training](https://mlsanity.com/paper/2211.12870/) (2022)
- [MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation](https://mlsanity.com/paper/2307.14336/) (2023)
- [Entropic Open-set Active Learning](https://mlsanity.com/paper/2312.14126/) (2023)
- [Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations](https://mlsanity.com/paper/2303.16891/) (2023)
- [What, How, and When Should Object Detectors Update in Continually Changing Test Domains?](https://mlsanity.com/paper/2312.08875/) (2023)
- [To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2307.15063/) (2023)
- [All-weather Multi-Modality Image Fusion: Unified Framework and 100k Benchmark](https://mlsanity.com/paper/2402.02090/) (2024)
- [UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps](https://mlsanity.com/paper/2403.17633/) (2024)
- [Bridging the Gap between Multi-focus and Multi-modal: A Focused Integration Framework for Multi-modal Image Fusion](https://mlsanity.com/paper/2311.01886/) (2023)
- [PosSAM: Panoptic Open-vocabulary Segment Anything](https://mlsanity.com/paper/2403.09620/) (2024)
- [Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning](https://mlsanity.com/paper/2406.11890/) (2024)
- [Source-free Domain Adaptive Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2401.17916/) (2024)
- [Brain-Inspired Online Adaptation for Remote Sensing with Spiking Neural Network](https://mlsanity.com/paper/2409.02146/) (2024)
- [MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection](https://mlsanity.com/paper/2406.14878/) (2024)
- [HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation](https://mlsanity.com/paper/2407.12387/) (2024)
- [Few-shot Online Anomaly Detection and Segmentation](https://mlsanity.com/paper/2403.18201/) (2024)
- [Continual Test-Time Adaptation for Object Detection with Adaptive Monitoring and Randomized Restoration](https://mlsanity.com/paper/2406.16439/) (2024)
- [Open-Set Automatic Target Recognition](https://mlsanity.com/paper/2211.05883/) (2022)
- [Channel-Selective Normalization for Label-Shift Robust Test-Time Adaptation](https://mlsanity.com/paper/2402.04958/) (2024)
- [Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detection](https://mlsanity.com/paper/2504.20498/) (2025)
- [Embodied Domain Adaptation for Object Detection](https://mlsanity.com/paper/2506.21860/) (2025)
- [Bayesian Test-time Adaptation for Object Recognition and Detection with Vision-language Models](https://mlsanity.com/paper/2510.02750/) (2025)
- [Improving Online Source-free Domain Adaptation for Object Detection by Unsupervised Data Acquisition](https://mlsanity.com/paper/2310.19258/) (2023)
- [Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher](https://mlsanity.com/paper/2407.07780/) (2024)
- [Improving Object Detection via Local-global Contrastive Learning](https://mlsanity.com/paper/2410.05058/) (2024)
- [CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving](https://mlsanity.com/paper/2505.16524/) (2025)
- [FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2605.03294/) (2026)
- [Unsupervised Cross-domain Pulmonary Nodule Detection without Source Data](https://mlsanity.com/paper/2304.01085/) (2023)

## Abstract (arXiv)

Existing object detection models assume both the training and test data are sampled from the same source domain. This assumption does not hold true when these detectors are deployed in real-world applications, where they encounter new visual domain. Unsupervised Domain Adaptation (UDA) methods are generally employed to mitigate the adverse effects caused by domain shift. Existing UDA methods operate in an offline manner where the model is first adapted towards the target domain and then deployed in real-world applications. However, this offline adaptation strategy is not suitable for real-world applications as the model frequently encounters new domain shifts. Hence, it becomes critical to develop a feasible UDA method that generalizes to these domain shifts encountered during deployment time in a continuous online manner. To this end, we propose a novel unified adaptation framework that adapts and improves generalization on the target domain in online settings. In particular, we introduce MemXformer - a cross-attention transformer-based memory module where items in the memory take advantage of domain shifts and record prototypical patterns of the target distribution. Further, MemXformer produces strong positive and negative pairs to guide a novel contrastive loss, which enhances target specific representation learning. Experiments on diverse detection benchmarks show that the proposed strategy can produce state-of-the-art performance in both online and offline settings. To the best of our knowledge, this is the first work to address online and offline adaptation settings for object detection. Code at https://github.com/Vibashan/memXformer-online-da