# Explainable Person Re-Identification with Attribute-guided Metric Distillation

arXiv: https://arxiv.org/abs/2103.01451 · HTML: https://mlsanity.com/paper/2103.01451/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 48 references that are in the map.
- First posted on arXiv 2 Mar 2021.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Omni-Scale Feature Learning for Person Re-Identification](https://mlsanity.com/paper/1905.00953/) (2019)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Harmonious Attention Network for Person Re-Identification](https://mlsanity.com/paper/1802.08122/) (2018)
- [Person Re-identification: Past, Present and Future](https://mlsanity.com/paper/1610.02984/) (2016)
- [FastReID: A Pytorch Toolbox for General Instance Re-identification](https://mlsanity.com/paper/2006.02631/) (2020)
- [A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification](https://mlsanity.com/paper/1906.08332/) (2019)
- [Relation-Aware Global Attention for Person Re-identification](https://mlsanity.com/paper/1904.02998/) (2019)
- [Improving Person Re-identification by Attribute and Identity Learning](https://mlsanity.com/paper/1703.07220/) (2017)
- [Interpreting CNNs via Decision Trees](https://mlsanity.com/paper/1802.00121/) (2018)
- [Black-box Explanation of Object Detectors via Saliency Maps](https://mlsanity.com/paper/2006.03204/) (2020)
- [Deeply-Learned Part-Aligned Representations for Person Re-Identification](https://mlsanity.com/paper/1707.07256/) (2017)
- [Mixed High-Order Attention Network for Person Re-Identification](https://mlsanity.com/paper/1908.05819/) (2019)
- [Attribution in Scale and Space](https://mlsanity.com/paper/2004.03383/) (2020)
- [Second-order Non-local Attention Networks for Person Re-identification](https://mlsanity.com/paper/1909.00295/) (2019)
- [A Richly Annotated Dataset for Pedestrian Attribute Recognition](https://mlsanity.com/paper/1603.07054/) (2016)

## Built on by (most cited first, 24 of 24)

- [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022)
- [Deep Frequency Filtering for Domain Generalization](https://mlsanity.com/paper/2203.12198/) (2022)
- [The State of Aerial Surveillance: A Survey](https://mlsanity.com/paper/2201.03080/) (2022)
- [Multi-Prompts Learning with Cross-Modal Alignment for Attribute-based Person Re-Identification](https://mlsanity.com/paper/2312.16797/) (2023)
- [AG-ReID.v2: Bridging Aerial and Ground Views for Person Re-identification](https://mlsanity.com/paper/2401.02634/) (2024)
- [Aerial-Ground Person Re-ID](https://mlsanity.com/paper/2303.08597/) (2023)
- [PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2304.07230/) (2023)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification](https://mlsanity.com/paper/2112.00317/) (2021)
- [VGSG: Vision-Guided Semantic-Group Network for Text-based Person Search](https://mlsanity.com/paper/2311.07514/) (2023)
- [Camera-aware Label Refinement for Unsupervised Person Re-identification](https://mlsanity.com/paper/2403.16450/) (2024)
- [Local-Aware Global Attention Network for Person Re-Identification Based on Body and Hand Images](https://mlsanity.com/paper/2209.04821/) (2022)
- [Learning Transferable Pedestrian Representation from Multimodal Information Supervision](https://mlsanity.com/paper/2304.05554/) (2023)
- [A Quantitative Evaluation of the Expressivity of BMI, Pose and Gender in Body Embeddings for Recognition and Identification](https://mlsanity.com/paper/2503.06451/) (2025)
- [TrackletGait: A Robust Framework for Gait Recognition in the Wild](https://mlsanity.com/paper/2508.02143/) (2025)
- [YYDS: Visible-Infrared Person Re-Identification with Coarse Descriptions](https://mlsanity.com/paper/2403.04183/) (2024)
- [Attribute Guidance With Inherent Pseudo-label For Occluded Person Re-identification](https://mlsanity.com/paper/2508.04998/) (2025)
- [Constructive Interpretability with CoLabel: Corroborative Integration, Complementary Features, and Collaborative Learning](https://mlsanity.com/paper/2205.10011/) (2022)
- [Revisiting the Role of Texture in 3D Person Re-identification](https://mlsanity.com/paper/2410.00348/) (2024)
- [S3CE-Net: Spike-guided Spatiotemporal Semantic Coupling and Expansion Network for Long Sequence Event Re-Identification](https://mlsanity.com/paper/2505.24401/) (2025)
- [ALADIN:Attribute-Language Distillation Network for Person Re-Identification](https://mlsanity.com/paper/2603.21482/) (2026)
- [AttriBE: Quantifying Attribute Expressivity in Body Embeddings for Recognition and Identification](https://mlsanity.com/paper/2604.27218/) (2026)
- [Collaborative Feature Aggregation for Face Super-Resolution and Robust Re-Identification](https://mlsanity.com/paper/2607.28130/) (2026)
- [Attribute-Centric Vision-Language Alignment for Fine-Grained Gait Understanding](https://mlsanity.com/paper/2610.14589/) (2026)

## Abstract (arXiv)

Despite the great progress of person re-identification (ReID) with the adoption of Convolutional Neural Networks, current ReID models are opaque and only outputs a scalar distance between two persons. There are few methods providing users semantically understandable explanations for why two persons are the same one or not. In this paper, we propose a post-hoc method, named Attribute-guided Metric Distillation (AMD), to explain existing ReID models. This is the first method to explore attributes to answer: 1) what and where the attributes make two persons different, and 2) how much each attribute contributes to the difference. In AMD, we design a pluggable interpreter network for target models to generate quantitative contributions of attributes and visualize accurate attention maps of the most discriminative attributes. To achieve this goal, we propose a metric distillation loss by which the interpreter learns to decompose the distance of two persons into components of attributes with knowledge distilled from the target model. Moreover, we propose an attribute prior loss to make the interpreter generate attribute-guided attention maps and to eliminate biases caused by the imbalanced distribution of attributes. This loss can guide the interpreter to focus on the exclusive and discriminative attributes rather than the large-area but common attributes of two persons. Comprehensive experiments show that the interpreter can generate effective and intuitive explanations for varied models and generalize well under cross-domain settings. As a by-product, the accuracy of target models can be further improved with our interpreter.