# Robust Re-Identification by Multiple Views Knowledge Distillation

arXiv: https://arxiv.org/abs/2007.04174 · HTML: https://mlsanity.com/paper/2007.04174/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2020.

## Built on by (most cited first, 29 of 29)

- [Lifelong Person Re-Identification via Adaptive Knowledge Accumulation](https://mlsanity.com/paper/2103.12462/) (2021)
- [How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting](https://mlsanity.com/paper/2203.04781/) (2022)
- [Visual Tuning](https://mlsanity.com/paper/2305.06061/) (2023)
- [Heterogeneous Relational Complement for Vehicle Re-identification](https://mlsanity.com/paper/2109.07894/) (2021)
- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval](https://mlsanity.com/paper/2202.06014/) (2022)
- [Multi-view Information Integration and Propagation for Occluded Person Re-identification](https://mlsanity.com/paper/2311.03828/) (2023)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Content-Variant Reference Image Quality Assessment via Knowledge Distillation](https://mlsanity.com/paper/2202.13123/) (2022)
- [Graph Convolution Based Efficient Re-Ranking for Visual Retrieval](https://mlsanity.com/paper/2306.08792/) (2023)
- [Learning to Disentangle Scenes for Person Re-identification](https://mlsanity.com/paper/2111.05476/) (2021)
- [Learning Comprehensive Representations with Richer Self for Text-to-Image Person Re-Identification](https://mlsanity.com/paper/2310.11210/) (2023)
- [Activity-Biometrics: Person Identification from Daily Activities](https://mlsanity.com/paper/2403.17360/) (2024)
- [AttributeNet: Attribute Enhanced Vehicle Re-Identification](https://mlsanity.com/paper/2102.03898/) (2021)
- [Graph Convolution for Re-ranking in Person Re-identification](https://mlsanity.com/paper/2107.02220/) (2021)
- [Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval](https://mlsanity.com/paper/2303.09230/) (2023)
- [Exploring Navigation Maps for Learning-Based Motion Prediction](https://mlsanity.com/paper/2302.06195/) (2023)
- [Improving Autonomous Driving Safety with POP: A Framework for Accurate Partially Observed Trajectory Predictions](https://mlsanity.com/paper/2309.15685/) (2023)
- [MovingFashion: a Benchmark for the Video-to-Shop Challenge](https://mlsanity.com/paper/2110.02627/) (2021)
- [Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval](https://mlsanity.com/paper/2210.10486/) (2022)
- [DisenQ: Disentangling Q-Former for Activity-Biometrics](https://mlsanity.com/paper/2507.07262/) (2025)
- [TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification](https://mlsanity.com/paper/2112.14239/) (2021)
- [MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networks](https://mlsanity.com/paper/2502.07422/) (2025)
- [Attribute Guided Sparse Tensor-Based Model for Person Re-Identification](https://mlsanity.com/paper/2108.04352/) (2021)
- [Image-to-Video Re-Identification via Mutual Discriminative Knowledge Transfer](https://mlsanity.com/paper/2201.08887/) (2022)
- [SRMAE: Masked Image Modeling for Scale-Invariant Deep Representations](https://mlsanity.com/paper/2308.08884/) (2023)
- [Hierarchical mutual distillation for multi-view fusion: Learning from all possible view combinations](https://mlsanity.com/paper/2411.10077/) (2024)
- [Evolution of ReID: From Early Methods to LLM Integration](https://mlsanity.com/paper/2506.13039/) (2025)
- [DARA: Degradation-Aware Low-Rank Residual Adaptation with Original-to-Corrupted Distillation for Corruption-Robust Animal Re-Identification](https://mlsanity.com/paper/2607.16644/) (2026)

## Abstract (arXiv)

To achieve robustness in Re-Identification, standard methods leverage tracking information in a Video-To-Video fashion. However, these solutions face a large drop in performance for single image queries (e.g., Image-To-Video setting). Recent works address this severe degradation by transferring temporal information from a Video-based network to an Image-based one. In this work, we devise a training strategy that allows the transfer of a superior knowledge, arising from a set of views depicting the target object. Our proposal - Views Knowledge Distillation (VKD) - pins this visual variety as a supervision signal within a teacher-student framework, where the teacher educates a student who observes fewer views. As a result, the student outperforms not only its teacher but also the current state-of-the-art in Image-To-Video by a wide margin (6.3% mAP on MARS, 8.6% on Duke-Video-ReId and 5% on VeRi-776). A thorough analysis - on Person, Vehicle and Animal Re-ID - investigates the properties of VKD from a qualitatively and quantitatively perspective. Code is available at https://github.com/aimagelab/VKD.