# PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data

arXiv: https://arxiv.org/abs/2005.00673 · HTML: https://mlsanity.com/paper/2005.00673/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2020.

## Built on by (most cited first, 30 of 31)

- [SynFace: Face Recognition with Synthetic Data](https://mlsanity.com/paper/2108.07960/) (2021)
- [GiT: Graph Interactive Transformer for Vehicle Re-identification](https://mlsanity.com/paper/2107.05475/) (2021)
- [The 5th AI City Challenge](https://mlsanity.com/paper/2104.12233/) (2021)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (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)
- [PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning](https://mlsanity.com/paper/2210.07886/) (2022)
- [Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification](https://mlsanity.com/paper/2108.09682/) (2021)
- [Multi-Target Multi-Camera Tracking of Vehicles using Metadata-Aided Re-ID and Trajectory-Based Camera Link Model](https://mlsanity.com/paper/2105.01213/) (2021)
- [Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning](https://mlsanity.com/paper/2108.02959/) (2021)
- [Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond](https://mlsanity.com/paper/2202.14034/) (2022)
- [Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems](https://mlsanity.com/paper/2110.07933/) (2021)
- [AttributeNet: Attribute Enhanced Vehicle Re-Identification](https://mlsanity.com/paper/2102.03898/) (2021)
- [ES-Net: Erasing Salient Parts to Learn More in Re-Identification](https://mlsanity.com/paper/2103.05918/) (2021)
- [HSGNet: Object Re-identification with Hierarchical Similarity Graph Network](https://mlsanity.com/paper/2211.05486/) (2022)
- [Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic](https://mlsanity.com/paper/2310.04416/) (2023)
- [Large-scale Training Data Search for Object Re-identification](https://mlsanity.com/paper/2303.16186/) (2023)
- [DVHN: A Deep Hashing Framework for Large-scale Vehicle Re-identification](https://mlsanity.com/paper/2112.04937/) (2021)
- [CityTrack: Improving City-Scale Multi-Camera Multi-Target Tracking by Location-Aware Tracking and Box-Grained Matching](https://mlsanity.com/paper/2307.02753/) (2023)
- [3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification](https://mlsanity.com/paper/2604.26520/) (2026)
- [Robust 2D/3D Vehicle Parsing in CVIS](https://mlsanity.com/paper/2103.06432/) (2021)
- [Pose Estimation and 3D Reconstruction of Vehicles from Stereo-Images Using a Subcategory-Aware Shape Prior](https://mlsanity.com/paper/2107.10898/) (2021)
- [Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identification](https://mlsanity.com/paper/2304.07883/) (2023)
- [Spatial-temporal Vehicle Re-identification](https://mlsanity.com/paper/2309.01166/) (2023)
- [Segment Any Vehicle: Semantic and Visual Context Driven SAM and A Benchmark](https://mlsanity.com/paper/2508.04260/) (2025)
- [SIRe-Networks: Convolutional Neural Networks Architectural Extension for Information Preservation via Skip/Residual Connections and Interlaced Auto-Encoders](https://mlsanity.com/paper/2110.02776/) (2021)
- [Image-to-Video Re-Identification via Mutual Discriminative Knowledge Transfer](https://mlsanity.com/paper/2201.08887/) (2022)
- [Self-supervised Geometric Features Discovery via Interpretable Attentio for Vehicle Re-Identification and Beyond (Complete Version)](https://mlsanity.com/paper/2303.11169/) (2023)
- [The Staged Knowledge Distillation in Video Classification: Harmonizing Student Progress by a Complementary Weakly Supervised Framework](https://mlsanity.com/paper/2307.05201/) (2023)
- [Object Re-identification via Spatial-temporal Fusion Networks and Causal Identity Matching](https://mlsanity.com/paper/2408.05558/) (2024)

## Abstract (arXiv)

In comparison with person re-identification (ReID), which has been widely studied in the research community, vehicle ReID has received less attention. Vehicle ReID is challenging due to 1) high intra-class variability (caused by the dependency of shape and appearance on viewpoint), and 2) small inter-class variability (caused by the similarity in shape and appearance between vehicles produced by different manufacturers). To address these challenges, we propose a Pose-Aware Multi-Task Re-Identification (PAMTRI) framework. This approach includes two innovations compared with previous methods. First, it overcomes viewpoint-dependency by explicitly reasoning about vehicle pose and shape via keypoints, heatmaps and segments from pose estimation. Second, it jointly classifies semantic vehicle attributes (colors and types) while performing ReID, through multi-task learning with the embedded pose representations. Since manually labeling images with detailed pose and attribute information is prohibitive, we create a large-scale highly randomized synthetic dataset with automatically annotated vehicle attributes for training. Extensive experiments validate the effectiveness of each proposed component, showing that PAMTRI achieves significant improvement over state-of-the-art on two mainstream vehicle ReID benchmarks: VeRi and CityFlow-ReID. Code and models are available at https://github.com/NVlabs/PAMTRI.