# Simulating Content Consistent Vehicle Datasets with Attribute Descent

arXiv: https://arxiv.org/abs/1912.08855 · HTML: https://mlsanity.com/paper/1912.08855/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2019.

## Built on by (most cited first, 30 of 36)

- [Fake It Till You Make It: Face analysis in the wild using synthetic data alone](https://mlsanity.com/paper/2109.15102/) (2021)
- [Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data](https://mlsanity.com/paper/2311.18729/) (2023)
- [The 5th AI City Challenge](https://mlsanity.com/paper/2104.12233/) (2021)
- [Heterogeneous Relational Complement for Vehicle Re-identification](https://mlsanity.com/paper/2109.07894/) (2021)
- [The 6th AI City Challenge](https://mlsanity.com/paper/2204.10380/) (2022)
- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification](https://mlsanity.com/paper/2109.10498/) (2021)
- [Multi-spectral Vehicle Re-identification with Cross-directional Consistency Network and a High-quality Benchmark](https://mlsanity.com/paper/2208.00632/) (2022)
- [Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification](https://mlsanity.com/paper/2108.09682/) (2021)
- [A Strong Baseline for Vehicle Re-Identification](https://mlsanity.com/paper/2104.10850/) (2021)
- [Synthehicle: Multi-Vehicle Multi-Camera Tracking in Virtual Cities](https://mlsanity.com/paper/2208.14167/) (2022)
- [Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond](https://mlsanity.com/paper/2202.14034/) (2022)
- [Ranking Models in Unlabeled New Environments](https://mlsanity.com/paper/2108.10310/) (2021)
- [Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Review](https://mlsanity.com/paper/2211.05120/) (2022)
- [An Empirical Study of Vehicle Re-Identification on the AI City Challenge](https://mlsanity.com/paper/2105.09701/) (2021)
- [RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-supervised Learning](https://mlsanity.com/paper/2209.08630/) (2022)
- [Mesh-Tension Driven Expression-Based Wrinkles for Synthetic Faces](https://mlsanity.com/paper/2210.03529/) (2022)
- [How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?](https://mlsanity.com/paper/2112.01730/) (2021)
- [Training with Product Digital Twins for AutoRetail Checkout](https://mlsanity.com/paper/2308.09708/) (2023)
- [Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic](https://mlsanity.com/paper/2310.04416/) (2023)
- [Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Correspondence](https://mlsanity.com/paper/2206.06424/) (2022)
- [Human Body Measurement Estimation with Adversarial Augmentation](https://mlsanity.com/paper/2210.05667/) (2022)
- [Large-scale Training Data Search for Object Re-identification](https://mlsanity.com/paper/2303.16186/) (2023)
- [VisionTraj: A Noise-Robust Trajectory Recovery Framework based on Large-scale Camera Network](https://mlsanity.com/paper/2312.06428/) (2023)
- [TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification](https://mlsanity.com/paper/2112.14239/) (2021)
- [Robust 2D/3D Vehicle Parsing in CVIS](https://mlsanity.com/paper/2103.06432/) (2021)
- [Synthetic Data Are as Good as the Real for Association Knowledge Learning in Multi-object Tracking](https://mlsanity.com/paper/2106.16100/) (2021)
- [Scalable and Real-time Multi-Camera Vehicle Detection, Re-Identification, and Tracking](https://mlsanity.com/paper/2204.07442/) (2022)
- [Enhancing Vehicle Re-identification and Matching for Weaving Analysis](https://mlsanity.com/paper/2407.04688/) (2024)
- [Measuring the Effect of Background on Classification and Feature Importance in Deep Learning for AV Perception](https://mlsanity.com/paper/2512.05937/) (2025)

## Abstract (arXiv)

This paper uses a graphic engine to simulate a large amount of training data with free annotations. Between synthetic and real data, there is a two-level domain gap, i.e., content level and appearance level. While the latter has been widely studied, we focus on reducing the content gap in attributes like illumination and viewpoint. To reduce the problem complexity, we choose a smaller and more controllable application, vehicle re-identification (re-ID). We introduce a large-scale synthetic dataset VehicleX. Created in Unity, it contains 1,362 vehicles of various 3D models with fully editable attributes. We propose an attribute descent approach to let VehicleX approximate the attributes in real-world datasets. Specifically, we manipulate each attribute in VehicleX, aiming to minimize the discrepancy between VehicleX and real data in terms of the Fr'echet Inception Distance (FID). This attribute descent algorithm allows content domain adaptation (DA) orthogonal to existing appearance DA methods. We mix the optimized VehicleX data with real-world vehicle re-ID datasets, and observe consistent improvement. With the augmented datasets, we report competitive accuracy. We make the dataset, engine and our codes available at https://github.com/yorkeyao/VehicleX.