# Automatic adaptation of object detectors to new domains using self-training

arXiv: https://arxiv.org/abs/1904.07305 · HTML: https://mlsanity.com/paper/1904.07305/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2019.

## Built on by (most cited first, 30 of 66)

- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Language Model Self-improvement by Reinforcement Learning Contemplation](https://mlsanity.com/paper/2305.14483/) (2023)
- [Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15793/) (2022)
- [An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions](https://mlsanity.com/paper/2204.08817/) (2022)
- [Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification](https://mlsanity.com/paper/2106.06133/) (2021)
- [Active Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2303.08348/) (2023)
- [Towards Online Domain Adaptive Object Detection](https://mlsanity.com/paper/2204.05289/) (2022)
- [Geometric Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16694/) (2021)
- [Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection](https://mlsanity.com/paper/2304.09446/) (2023)
- [CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection](https://mlsanity.com/paper/2212.00244/) (2022)
- [Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning](https://mlsanity.com/paper/2110.03143/) (2021)
- [Adversarial Alignment for Source Free Object Detection](https://mlsanity.com/paper/2301.04265/) (2023)
- [Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection](https://mlsanity.com/paper/2110.00249/) (2021)
- [Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection](https://mlsanity.com/paper/2103.14198/) (2021)
- [Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking](https://mlsanity.com/paper/2204.07049/) (2022)
- [AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection](https://mlsanity.com/paper/2106.05499/) (2021)
- [DARTH: Holistic Test-time Adaptation for Multiple Object Tracking](https://mlsanity.com/paper/2310.01926/) (2023)
- [What, How, and When Should Object Detectors Update in Continually Changing Test Domains?](https://mlsanity.com/paper/2312.08875/) (2023)
- [Optimizing Language Model's Reasoning Abilities with Weak Supervision](https://mlsanity.com/paper/2405.04086/) (2024)
- [Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection](https://mlsanity.com/paper/2111.15656/) (2021)
- [Align and Distill: Unifying and Improving Domain Adaptive Object Detection](https://mlsanity.com/paper/2403.12029/) (2024)
- [Noisy student-teacher training for robust keyword spotting](https://mlsanity.com/paper/2106.01604/) (2021)
- [FAST3D: Flow-Aware Self-Training for 3D Object Detectors](https://mlsanity.com/paper/2110.09355/) (2021)
- [TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning](https://mlsanity.com/paper/2209.01373/) (2022)
- [Unsupervised Domain Adaptive Detection with Network Stability Analysis](https://mlsanity.com/paper/2308.08182/) (2023)

## Abstract (arXiv)

This work addresses the unsupervised adaptation of an existing object detector to a new target domain. We assume that a large number of unlabeled videos from this domain are readily available. We automatically obtain labels on the target data by using high-confidence detections from the existing detector, augmented with hard (misclassified) examples acquired by exploiting temporal cues using a tracker. These automatically-obtained labels are then used for re-training the original model. A modified knowledge distillation loss is proposed, and we investigate several ways of assigning soft-labels to the training examples from the target domain. Our approach is empirically evaluated on challenging face and pedestrian detection tasks: a face detector trained on WIDER-Face, which consists of high-quality images crawled from the web, is adapted to a large-scale surveillance data set; a pedestrian detector trained on clear, daytime images from the BDD-100K driving data set is adapted to all other scenarios such as rainy, foggy, night-time. Our results demonstrate the usefulness of incorporating hard examples obtained from tracking, the advantage of using soft-labels via distillation loss versus hard-labels, and show promising performance as a simple method for unsupervised domain adaptation of object detectors, with minimal dependence on hyper-parameters.