# Vehicle Re-identification with Viewpoint-aware Metric Learning

arXiv: https://arxiv.org/abs/1910.04104 · HTML: https://mlsanity.com/paper/1910.04104/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2019.

## Built on by (most cited first, 30 of 45)

- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification](https://mlsanity.com/paper/2108.08728/) (2021)
- [State Space Model for New-Generation Network Alternative to Transformers: A Survey](https://mlsanity.com/paper/2404.09516/) (2024)
- [GiT: Graph Interactive Transformer for Vehicle Re-identification](https://mlsanity.com/paper/2107.05475/) (2021)
- [Heterogeneous Relational Complement for Vehicle Re-identification](https://mlsanity.com/paper/2109.07894/) (2021)
- [Multi-Scale Aligned Distillation for Low-Resolution Detection](https://mlsanity.com/paper/2109.06875/) (2021)
- [Adaptive Sparse Pairwise Loss for Object Re-Identification](https://mlsanity.com/paper/2303.18247/) (2023)
- [Multi-spectral Vehicle Re-identification with Cross-directional Consistency Network and a High-quality Benchmark](https://mlsanity.com/paper/2208.00632/) (2022)
- [Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identification](https://mlsanity.com/paper/2301.09498/) (2023)
- [CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation](https://mlsanity.com/paper/2112.04966/) (2021)
- [Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond](https://mlsanity.com/paper/2202.14034/) (2022)
- [A Comprehensive Survey on Deep-Learning-based Vehicle Re-Identification: Models, Data Sets and Challenges](https://mlsanity.com/paper/2401.10643/) (2024)
- [Other Tokens Matter: Exploring Global and Local Features of Vision Transformers for Object Re-Identification](https://mlsanity.com/paper/2404.14985/) (2024)
- [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)
- [Improving Deep Metric Learning by Divide and Conquer](https://mlsanity.com/paper/2109.04003/) (2021)
- [Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization](https://mlsanity.com/paper/2210.01908/) (2022)
- [Unsupervised Vehicle Re-Identification via Self-supervised Metric Learning using Feature Dictionary](https://mlsanity.com/paper/2103.02250/) (2021)
- [Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching](https://mlsanity.com/paper/2203.15285/) (2022)
- [Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey](https://mlsanity.com/paper/2412.00348/) (2024)
- [Rethinking Deep Contrastive Learning with Embedding Memory](https://mlsanity.com/paper/2103.14003/) (2021)
- [Hierarchical Image Classification with A Literally Toy Dataset](https://mlsanity.com/paper/2111.00892/) (2021)
- [DVHN: A Deep Hashing Framework for Large-scale Vehicle Re-identification](https://mlsanity.com/paper/2112.04937/) (2021)
- [Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2112.07966/) (2021)
- [Symmetric Network with Spatial Relationship Modeling for Natural Language-based Vehicle Retrieval](https://mlsanity.com/paper/2206.10879/) (2022)
- [Style Variable and Irrelevant Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2209.05235/) (2022)
- [DenoiseRep: Denoising Model for Representation Learning](https://mlsanity.com/paper/2406.08773/) (2024)
- [Vehicle Re-identification Method Based on Vehicle Attribute and Mutual Exclusion Between Cameras](https://mlsanity.com/paper/2104.14882/) (2021)

## Abstract (arXiv)

This paper considers vehicle re-identification (re-ID) problem. The extreme viewpoint variation (up to 180 degrees) poses great challenges for existing approaches. Inspired by the behavior in human's recognition process, we propose a novel viewpoint-aware metric learning approach. It learns two metrics for similar viewpoints and different viewpoints in two feature spaces, respectively, giving rise to viewpoint-aware network (VANet). During training, two types of constraints are applied jointly. During inference, viewpoint is firstly estimated and the corresponding metric is used. Experimental results confirm that VANet significantly improves re-ID accuracy, especially when the pair is observed from different viewpoints. Our method establishes the new state-of-the-art on two benchmarks.