# Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection

arXiv: https://arxiv.org/abs/2110.00249 · HTML: https://mlsanity.com/paper/2110.00249/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 56 references that are in the map.
- First posted on arXiv 1 Oct 2021.

## Builds on (most cited first, 30 of 45)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [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)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [A DIRT-T Approach to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1802.08735/) (2018)
- [UnitBox: An Advanced Object Detection Network](https://mlsanity.com/paper/1608.01471/) (2016)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/1910.13049/) (2019)
- [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)
- [Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection](https://mlsanity.com/paper/1905.05396/) (2019)
- [An Analysis of Scale Invariance in Object Detection - SNIP](https://mlsanity.com/paper/1711.08189/) (2017)

## Built on by (most cited first, 24 of 24)

- [SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.06398/) (2022)
- [Multi-Granularity Alignment Domain Adaptation for Object Detection](https://mlsanity.com/paper/2203.16897/) (2022)
- [Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment](https://mlsanity.com/paper/2405.14497/) (2024)
- [Towards Improving Calibration in Object Detection Under Domain Shift](https://mlsanity.com/paper/2209.07601/) (2022)
- [Towards Robust Adaptive Object Detection under Noisy Annotations](https://mlsanity.com/paper/2204.02620/) (2022)
- [SCoDA: Domain Adaptive Shape Completion for Real Scans](https://mlsanity.com/paper/2304.10179/) (2023)
- [Robust Domain Adaptive Object Detection with Unified Multi-Granularity Alignment](https://mlsanity.com/paper/2301.00371/) (2023)
- [Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning](https://mlsanity.com/paper/2311.04815/) (2023)
- [Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors](https://mlsanity.com/paper/2309.08771/) (2023)
- [DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection](https://mlsanity.com/paper/2311.10437/) (2023)
- [D-MASTER: Mask Annealed Transformer for Unsupervised Domain Adaptation in Breast Cancer Detection from Mammograms](https://mlsanity.com/paper/2407.06585/) (2024)
- [Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond](https://mlsanity.com/paper/2303.10343/) (2023)
- [Cross-domain Detection Transformer based on Spatial-aware and Semantic-aware Token Alignment](https://mlsanity.com/paper/2206.00222/) (2022)
- [Distribution Regularized Self-Supervised Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2206.09683/) (2022)
- [Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2408.02039/) (2024)
- [Unsupervised Domain Adaptation for One-stage Object Detector using Offsets to Bounding Box](https://mlsanity.com/paper/2207.09656/) (2022)
- [SF-FSDA: Source-Free Few-Shot Domain Adaptive Object Detection with Efficient Labeled Data Factory](https://mlsanity.com/paper/2306.04385/) (2023)
- [arXiVeri: Automatic table verification with GPT](https://mlsanity.com/paper/2306.07968/) (2023)
- [Leveraging Topology for Domain Adaptive Road Segmentation in Satellite and Aerial Imagery](https://mlsanity.com/paper/2309.15625/) (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)
- [Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis](https://mlsanity.com/paper/2312.02826/) (2023)
- [Utilizing Graph Generation for Enhanced Domain Adaptive Object Detection](https://mlsanity.com/paper/2406.06535/) (2024)
- [CLDA-YOLO: Visual Contrastive Learning Based Domain Adaptive YOLO Detector](https://mlsanity.com/paper/2412.11812/) (2024)

## Abstract (arXiv)

We study adapting trained object detectors to unseen domains manifesting significant variations of object appearance, viewpoints and backgrounds. Most current methods align domains by either using image or instance-level feature alignment in an adversarial fashion. This often suffers due to the presence of unwanted background and as such lacks class-specific alignment. A common remedy to promote class-level alignment is to use high confidence predictions on the unlabelled domain as pseudo labels. These high confidence predictions are often fallacious since the model is poorly calibrated under domain shift. In this paper, we propose to leverage model predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment. Specifically, we measure predictive uncertainty on class assignments and the bounding box predictions. Model predictions with low uncertainty are used to generate pseudo-labels for self-supervision, whereas the ones with higher uncertainty are used to generate tiles for an adversarial feature alignment stage. This synergy between tiling around the uncertain object regions and generating pseudo-labels from highly certain object regions allows us to capture both the image and instance level context during the model adaptation stage. We perform extensive experiments covering various domain shift scenarios. Our approach improves upon existing state-of-the-art methods with visible margins.