# Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night

arXiv: https://arxiv.org/abs/1907.08719 · HTML: https://mlsanity.com/paper/1907.08719/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2019.

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

- [Model-Based Domain Generalization](https://mlsanity.com/paper/2102.11436/) (2021)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Spectral Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2106.06112/) (2021)
- [HLA-Face: Joint High-Low Adaptation for Low Light Face Detection](https://mlsanity.com/paper/2104.01984/) (2021)
- [DA-DETR: Domain Adaptive Detection Transformer with Information Fusion](https://mlsanity.com/paper/2103.17084/) (2021)
- [Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domains](https://mlsanity.com/paper/2304.02950/) (2023)
- [Day-to-Night Image Synthesis for Training Nighttime Neural ISPs](https://mlsanity.com/paper/2206.02715/) (2022)
- [Multi-Source Domain Adaptation for Object Detection](https://mlsanity.com/paper/2106.15793/) (2021)
- [Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2312.01220/) (2023)
- [Mutually improved endoscopic image synthesis and landmark detection in unpaired image-to-image translation](https://mlsanity.com/paper/2107.06941/) (2021)
- [Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation](https://mlsanity.com/paper/2407.13524/) (2024)
- [Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework](https://mlsanity.com/paper/2310.15646/) (2023)
- [Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2307.08779/) (2023)
- [Towards Full-scene Domain Generalization in Multi-agent Collaborative Bird's Eye View Segmentation for Connected and Autonomous Driving](https://mlsanity.com/paper/2311.16754/) (2023)
- [Six-channel Image Representation for Cross-domain Object Detection](https://mlsanity.com/paper/2101.00561/) (2021)
- [Integrated Multiscale Domain Adaptive YOLO](https://mlsanity.com/paper/2202.03527/) (2022)
- [Domain Adaptive Person Search](https://mlsanity.com/paper/2207.11898/) (2022)
- [An Unsupervised Domain Adaptive Approach for Multimodal 2D Object Detection in Adverse Weather Conditions](https://mlsanity.com/paper/2203.03568/) (2022)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Assessing Domain Gap for Continual Domain Adaptation in Object Detection](https://mlsanity.com/paper/2302.10396/) (2023)
- [Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning](https://mlsanity.com/paper/2309.16351/) (2023)
- [Multi-Target Domain Adaptation via Unsupervised Domain Classification for Weather Invariant Object Detection](https://mlsanity.com/paper/2103.13970/) (2021)
- [RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions](https://mlsanity.com/paper/2109.01820/) (2021)
- [Seeing Objects in dark with Continual Contrastive Learning](https://mlsanity.com/paper/2112.02891/) (2021)
- [Homography Guided Temporal Fusion for Road Line and Marking Segmentation](https://mlsanity.com/paper/2404.07626/) (2024)
- [Deep Domain Adaptation for Detecting Bomb Craters in Aerial Images](https://mlsanity.com/paper/2209.11299/) (2022)
- [Cross-Domain Object Detection Using Unsupervised Image Translation](https://mlsanity.com/paper/2601.11779/) (2026)
- [Multi Self-supervised Pre-fine-tuned Transformer Fusion for Better Intelligent Transportation Detection](https://mlsanity.com/paper/2310.11307/) (2023)
- [RainSD: Rain Style Diversification Module for Image Synthesis Enhancement using Feature-Level Style Distribution](https://mlsanity.com/paper/2401.00460/) (2023)
- [Implicit Non-Causal Factors are Out via Dataset Splitting for Domain Generalization Object Detection](https://mlsanity.com/paper/2601.19127/) (2026)

## Abstract (arXiv)

Deep learning techniques have enabled the emergence of state-of-the-art models to address object detection tasks. However, these techniques are data-driven, delegating the accuracy to the training dataset which must resemble the images in the target task. The acquisition of a dataset involves annotating images, an arduous and expensive process, generally requiring time and manual effort. Thus, a challenging scenario arises when the target domain of application has no annotated dataset available, making tasks in such situation to lean on a training dataset of a different domain. Sharing this issue, object detection is a vital task for autonomous vehicles where the large amount of driving scenarios yields several domains of application requiring annotated data for the training process. In this work, a method for training a car detection system with annotated data from a source domain (day images) without requiring the image annotations of the target domain (night images) is presented. For that, a model based on Generative Adversarial Networks (GANs) is explored to enable the generation of an artificial dataset with its respective annotations. The artificial dataset (fake dataset) is created translating images from day-time domain to night-time domain. The fake dataset, which comprises annotated images of only the target domain (night images), is then used to train the car detector model. Experimental results showed that the proposed method achieved significant and consistent improvements, including the increasing by more than 10% of the detection performance when compared to the training with only the available annotated data (i.e., day images).