# Generalization Limits in Vehicle Re-Identification

arXiv: https://arxiv.org/abs/2606.01981 · HTML: https://mlsanity.com/paper/2606.01981/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Deep Face Recognition: A Survey](https://mlsanity.com/paper/1804.06655/) (2018)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification](https://mlsanity.com/paper/1903.09254/) (2019)
- [Dissecting Person Re-identification from the Viewpoint of Viewpoint](https://mlsanity.com/paper/1812.02162/) (2018)
- [Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification](https://mlsanity.com/paper/2205.02151/) (2022)
- [Triplet-Center Loss for Multi-View 3D Object Retrieval](https://mlsanity.com/paper/1803.06189/) (2018)
- [Improved Embeddings with Easy Positive Triplet Mining](https://mlsanity.com/paper/1904.04370/) (2019)
- [WildlifeDatasets: An open-source toolkit for animal re-identification](https://mlsanity.com/paper/2311.09118/) (2023)
- [A survey of advances in vision-based vehicle re-identification](https://mlsanity.com/paper/1905.13258/) (2019)
- [Self-Supervised Pre-Training for Transformer-Based Person Re-Identification](https://mlsanity.com/paper/2111.12084/) (2021)
- [PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data](https://mlsanity.com/paper/2005.00673/) (2020)
- [Improving Shadow Suppression for Illumination Robust Face Recognition](https://mlsanity.com/paper/1710.05073/) (2017)
- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [In Defense of the Classification Loss for Person Re-Identification](https://mlsanity.com/paper/1809.05864/) (2018)
- [Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identification](https://mlsanity.com/paper/2301.09498/) (2023)
- [Searching for Alignment in Face Recognition](https://mlsanity.com/paper/2102.05447/) (2021)
- [Rotation Invariant Transformer for Recognizing Object in UAVs](https://mlsanity.com/paper/2311.02559/) (2023)

## Abstract (arXiv)

Vehicle re-identification focuses on retrieving images of the same vehicle from a gallery given a query image. Upon closer inspection of commonly used datasets, we observe that vehicles with few visual differences-e.g., the same make, model, and color-appear in both the training and test sets. As a result, methods that effectively memorize the training data tend to perform well on these test sets but struggle to generalize to other datasets. In this paper, we address this issue by proposing a novel evaluation approach that more effectively measures generalization capability to unseen vehicle types. To further study generalization performance, we also propose splitting the evaluation based on view, allowing us to differentiate the effect of viewpoint robustness from that of same-view re-identification. Our findings reveal that most state-of-the-art methods struggle with unseen vehicle types, and that their robustness to viewpoint changes and attention to detail are limited to vehicle types seen during training.