# STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization

arXiv: https://arxiv.org/abs/2303.17937 · HTML: https://mlsanity.com/paper/2303.17937/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 50 references that are in the map.
- First posted on arXiv 31 Mar 2023.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation](https://mlsanity.com/paper/2208.05117/) (2022)
- [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)
- [Cycle Self-Training for Domain Adaptation](https://mlsanity.com/paper/2103.03571/) (2021)
- [Multi-adversarial Faster-RCNN for Unrestricted Object Detection](https://mlsanity.com/paper/1907.10343/) (2019)
- [A Robust Learning Approach to Domain Adaptive Object Detection](https://mlsanity.com/paper/1904.02361/) (2019)

## Built on by (most cited first, 13 of 13)

- [PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images](https://mlsanity.com/paper/2409.13401/) (2024)
- [What, How, and When Should Object Detectors Update in Continually Changing Test Domains?](https://mlsanity.com/paper/2312.08875/) (2023)
- [On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning](https://mlsanity.com/paper/2410.04682/) (2024)
- [Test-Time Adaptive Object Detection with Foundation Model](https://mlsanity.com/paper/2510.25175/) (2025)
- [VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors](https://mlsanity.com/paper/2510.00458/) (2025)
- [Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection](https://mlsanity.com/paper/2405.18911/) (2024)
- [Bayesian Test-time Adaptation for Object Recognition and Detection with Vision-language Models](https://mlsanity.com/paper/2510.02750/) (2025)
- [Context Enhanced Transformer for Single Image Object Detection](https://mlsanity.com/paper/2312.14492/) (2023)
- [Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios](https://mlsanity.com/paper/2506.24063/) (2025)
- [FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2605.03294/) (2026)
- [Reward-Guided Semantic Evolution for Test-time Adaptive Object Detection](https://mlsanity.com/paper/2605.04531/) (2026)
- [DESA-TTA: Dynamic EMA and Source Anchoring for Test-Time Adaptation](https://mlsanity.com/paper/2609.01795/) (2026)
- [Robust Online Aero-Engine Blade Defect Detection via Dual-Alignment Test-Time Adaptation](https://mlsanity.com/paper/2610.00067/) (2026)

## Abstract (arXiv)

Domain adaptation helps generalizing object detection models to target domain data with distribution shift. It is often achieved by adapting with access to the whole target domain data. In a more realistic scenario, target distribution is often unpredictable until inference stage. This motivates us to explore adapting an object detection model at test-time, a.k.a. test-time adaptation (TTA). In this work, we approach test-time adaptive object detection (TTAOD) from two perspective. First, we adopt a self-training paradigm to generate pseudo labeled objects with an exponential moving average model. The pseudo labels are further used to supervise adapting source domain model. As self-training is prone to incorrect pseudo labels, we further incorporate aligning feature distributions at two output levels as regularizations to self-training. To validate the performance on TTAOD, we create benchmarks based on three standard object detection datasets and adapt generic TTA methods to object detection task. Extensive evaluations suggest our proposed method sets the state-of-the-art on test-time adaptive object detection task.