# Contrastive Mean Teacher for Domain Adaptive Object Detectors

arXiv: https://arxiv.org/abs/2305.03034 · HTML: https://mlsanity.com/paper/2305.03034/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 47 references that are in the map.
- First posted on arXiv 4 May 2023.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (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)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (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)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals](https://mlsanity.com/paper/2102.06191/) (2021)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [Efficient Visual Pretraining with Contrastive Detection](https://mlsanity.com/paper/2103.10957/) (2021)
- [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://mlsanity.com/paper/1904.11245/) (2019)
- [Progressive Domain Adaptation for Object Detection](https://mlsanity.com/paper/1910.11319/) (2019)
- [Exploring Categorical Regularization for Domain Adaptive Object Detection](https://mlsanity.com/paper/2003.09152/) (2020)
- [Harmonizing Transferability and Discriminability for Adapting Object Detectors](https://mlsanity.com/paper/2003.06297/) (2020)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection](https://mlsanity.com/paper/1905.05396/) (2019)
- [Aligning Pretraining for Detection via Object-Level Contrastive Learning](https://mlsanity.com/paper/2106.02637/) (2021)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)

## Built on by (most cited first, 30 of 53)

- [CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection](https://mlsanity.com/paper/2403.19278/) (2024)
- [Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection](https://mlsanity.com/paper/2407.11499/) (2024)
- [DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment](https://mlsanity.com/paper/2405.11765/) (2024)
- [Align and Distill: Unifying and Improving Domain Adaptive Object Detection](https://mlsanity.com/paper/2403.12029/) (2024)
- [D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection](https://mlsanity.com/paper/2403.09359/) (2024)
- [BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation](https://mlsanity.com/paper/2403.15019/) (2024)
- [Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection](https://mlsanity.com/paper/2503.23220/) (2025)
- [Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection](https://mlsanity.com/paper/2503.02101/) (2025)
- [DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection](https://mlsanity.com/paper/2311.10437/) (2023)
- [BlenDA: Domain Adaptive Object Detection through diffusion-based blending](https://mlsanity.com/paper/2401.09921/) (2024)
- [Versatile Teacher: A Class-aware Teacher-student Framework for Cross-domain Adaptation](https://mlsanity.com/paper/2405.11754/) (2024)
- [Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View](https://mlsanity.com/paper/2407.12870/) (2024)
- [Towards Unsupervised Model Selection for Domain Adaptive Object Detection](https://mlsanity.com/paper/2412.17284/) (2024)
- [SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems](https://mlsanity.com/paper/2504.15728/) (2025)
- [Source-Free Object Detection with Detection Transformer](https://mlsanity.com/paper/2510.11090/) (2025)
- [Enhancing cross-domain detection: adaptive class-aware contrastive transformer](https://mlsanity.com/paper/2401.13264/) (2024)
- [DG-DETR: Toward Domain Generalized Detection Transformer](https://mlsanity.com/paper/2504.19574/) (2025)
- [Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions](https://mlsanity.com/paper/2404.15252/) (2024)
- [Few-Shot Domain Adaptive Object Detection for Microscopic Images](https://mlsanity.com/paper/2407.07633/) (2024)
- [Quantifying Context Bias in Domain Adaptation for Object Detection](https://mlsanity.com/paper/2409.14679/) (2024)
- [MVUDA: Unsupervised Domain Adaptation for Multi-view Pedestrian Detection](https://mlsanity.com/paper/2412.04117/) (2024)
- [Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariance](https://mlsanity.com/paper/2502.03835/) (2025)
- [DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object Detection](https://mlsanity.com/paper/2502.11178/) (2025)
- [Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability](https://mlsanity.com/paper/2506.21042/) (2025)
- [Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions](https://mlsanity.com/paper/2403.15786/) (2024)
- [Towards Adaptive Pseudo-label Learning for Semi-Supervised Temporal Action Localization](https://mlsanity.com/paper/2407.07673/) (2024)
- [Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher](https://mlsanity.com/paper/2407.07780/) (2024)
- [Domain Adaptive Lung Nodule Detection in X-ray Image](https://mlsanity.com/paper/2407.19397/) (2024)
- [Improving Object Detection via Local-global Contrastive Learning](https://mlsanity.com/paper/2410.05058/) (2024)
- [IndraEye: Infrared Electro-Optical UAV-based Perception Dataset for Robust Downstream Tasks](https://mlsanity.com/paper/2410.20953/) (2024)

## Abstract (arXiv)

Object detectors often suffer from the domain gap between training (source domain) and real-world applications (target domain). Mean-teacher self-training is a powerful paradigm in unsupervised domain adaptation for object detection, but it struggles with low-quality pseudo-labels. In this work, we identify the intriguing alignment and synergy between mean-teacher self-training and contrastive learning. Motivated by this, we propose Contrastive Mean Teacher (CMT) -- a unified, general-purpose framework with the two paradigms naturally integrated to maximize beneficial learning signals. Instead of using pseudo-labels solely for final predictions, our strategy extracts object-level features using pseudo-labels and optimizes them via contrastive learning, without requiring labels in the target domain. When combined with recent mean-teacher self-training methods, CMT leads to new state-of-the-art target-domain performance: 51.9% mAP on Foggy Cityscapes, outperforming the previously best by 2.1% mAP. Notably, CMT can stabilize performance and provide more significant gains as pseudo-label noise increases.