# Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond

arXiv: https://arxiv.org/abs/2010.09221 · HTML: https://mlsanity.com/paper/2010.09221/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 25 of 25)

- [EventGPT: Event Stream Understanding with Multimodal Large Language Models](https://mlsanity.com/paper/2412.00832/) (2024)
- [Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors](https://mlsanity.com/paper/2503.20211/) (2025)
- [Adaptive Sparse Pairwise Loss for Object Re-Identification](https://mlsanity.com/paper/2303.18247/) (2023)
- [Video-based Visible-Infrared Person Re-Identification with Auxiliary Samples](https://mlsanity.com/paper/2311.15571/) (2023)
- [A Comprehensive Survey on Deep-Learning-based Vehicle Re-Identification: Models, Data Sets and Challenges](https://mlsanity.com/paper/2401.10643/) (2024)
- [Rethinking Person Re-identification from a Projection-on-Prototypes Perspective](https://mlsanity.com/paper/2308.10717/) (2023)
- [TextSplat: Text-Guided Semantic Fusion for Generalizable Gaussian Splatting](https://mlsanity.com/paper/2504.09588/) (2025)
- [RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-supervised Learning](https://mlsanity.com/paper/2209.08630/) (2022)
- [Strength in Diversity: Multi-Branch Representation Learning for Vehicle Re-Identification](https://mlsanity.com/paper/2310.01129/) (2023)
- [Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery](https://mlsanity.com/paper/2605.01191/) (2026)
- [CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning](https://mlsanity.com/paper/2605.29602/) (2026)
- [Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification](https://mlsanity.com/paper/2207.09884/) (2022)
- [EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients](https://mlsanity.com/paper/2412.00334/) (2024)
- [SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling](https://mlsanity.com/paper/2605.30750/) (2026)
- [Multi-Attention-Based Soft Partition Network for Vehicle Re-Identification](https://mlsanity.com/paper/2104.10401/) (2021)
- [Scalable and Real-time Multi-Camera Vehicle Detection, Re-Identification, and Tracking](https://mlsanity.com/paper/2204.07442/) (2022)
- [SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding](https://mlsanity.com/paper/2505.17674/) (2025)
- [Dual Cluster Contrastive learning for Object Re-Identification](https://mlsanity.com/paper/2112.04662/) (2021)
- [Scalable Vehicle Re-Identification via Self-Supervision](https://mlsanity.com/paper/2205.07613/) (2022)
- [Uncertainty Quantification via H"older Divergence for Multi-View Representation Learning](https://mlsanity.com/paper/2411.00826/) (2024)
- [Robust Brain Tumor Segmentation with Incomplete MRI Modalities Using H"older Divergence and Mutual Information-Enhanced Knowledge Transfer](https://mlsanity.com/paper/2507.01254/) (2025)
- [Similarity-based Outlier Detection for Noisy Object Re-Identification Using Beta Mixtures](https://mlsanity.com/paper/2509.08926/) (2025)
- [VSE-MOT: Multi-Object Tracking in Low-Quality Video Scenes Guided by Visual Semantic Enhancement](https://mlsanity.com/paper/2509.14060/) (2025)
- [Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender Systems](https://mlsanity.com/paper/2603.12752/) (2026)
- [Lookalike3D: Seeing Double in 3D](https://mlsanity.com/paper/2603.24713/) (2026)

## Abstract (arXiv)

To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors. In this paper, we seek to achieve the similar goal but do not involve more human efforts. To this end, we introduce a novel framework, which successfully encodes both geometric local features and global representations to distinguish vehicle instances, optimized only by the supervision from official ID labels. Specifically, given our insight that objects in ReID share similar geometric characteristics, we propose to borrow self-supervised representation learning to facilitate geometric features discovery. To condense these features, we introduce an interpretable attention module, with the core of local maxima aggregation instead of fully automatic learning, whose mechanism is completely understandable and whose response map is physically reasonable. To the best of our knowledge, we are the first that perform self-supervised learning to discover geometric features. We conduct comprehensive experiments on three most popular datasets for vehicle ReID, i.e., VeRi-776, CityFlow-ReID, and VehicleID. We report our state-of-the-art (SOTA) performances and promising visualization results. We also show the excellent scalability of our approach on other ReID related tasks, i.e., person ReID and multi-target multi-camera (MTMC) vehicle tracking.