# Proto2Proto: Can you recognize the car, the way I do?

arXiv: https://arxiv.org/abs/2204.11830 · HTML: https://mlsanity.com/paper/2204.11830/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 53 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [Variational Information Distillation for Knowledge Transfer](https://mlsanity.com/paper/1904.05835/) (2019)
- [Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks](https://mlsanity.com/paper/2004.05937/) (2020)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Correlation Congruence for Knowledge Distillation](https://mlsanity.com/paper/1904.01802/) (2019)
- [On Completeness-aware Concept-Based Explanations in Deep Neural Networks](https://mlsanity.com/paper/1910.07969/) (2019)
- [Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons](https://mlsanity.com/paper/1811.03233/) (2018)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Knowledge Distillation Meets Self-Supervision](https://mlsanity.com/paper/2006.07114/) (2020)
- [ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery](https://mlsanity.com/paper/2011.14340/) (2020)
- [Adaptive Neural Trees](https://mlsanity.com/paper/1807.06699/) (2018)
- [Interpreting Black Box Predictions using Fisher Kernels](https://mlsanity.com/paper/1810.10118/) (2018)
- [NBDT: Neural-Backed Decision Trees](https://mlsanity.com/paper/2004.00221/) (2020)

## Built on by (most cited first, 23 of 23)

- [ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition](https://mlsanity.com/paper/2208.10431/) (2022)
- [Learning Support and Trivial Prototypes for Interpretable Image Classification](https://mlsanity.com/paper/2301.04011/) (2023)
- [ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts](https://mlsanity.com/paper/2301.12276/) (2023)
- [ICICLE: Interpretable Class Incremental Continual Learning](https://mlsanity.com/paper/2303.07811/) (2023)
- [Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery](https://mlsanity.com/paper/2410.19213/) (2024)
- [Pixel-Grounded Prototypical Part Networks](https://mlsanity.com/paper/2309.14531/) (2023)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision](https://mlsanity.com/paper/2405.14331/) (2024)
- [Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons](https://mlsanity.com/paper/2502.03391/) (2025)
- [Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition](https://mlsanity.com/paper/2312.00092/) (2023)
- [Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement](https://mlsanity.com/paper/2311.15303/) (2023)
- [A survey on Concept-based Approaches For Model Improvement](https://mlsanity.com/paper/2403.14566/) (2024)
- [Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.11145/) (2023)
- [SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence](https://mlsanity.com/paper/2507.19321/) (2025)
- [PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans](https://mlsanity.com/paper/2308.13651/) (2023)
- [Language Model as Visual Explainer](https://mlsanity.com/paper/2412.07802/) (2024)
- [This looks like what? Challenges and Future Research Directions for Part-Prototype Models](https://mlsanity.com/paper/2502.09340/) (2025)
- [ProtoSolo: Interpretable Image Classification via Single-Prototype Activation](https://mlsanity.com/paper/2506.19808/) (2025)
- [CIP-Net: Continual Interpretable Prototype-based Network](https://mlsanity.com/paper/2512.07981/) (2025)
- [UIPC-MF: User-Item Prototype Connection Matrix Factorization for Explainable Collaborative Filtering](https://mlsanity.com/paper/2308.07048/) (2023)
- [FeaInfNet: Diagnosis in Medical Image with Feature-Driven Inference and Visual Explanations](https://mlsanity.com/paper/2312.01871/) (2023)
- [Prototype Guided Backdoor Defense](https://mlsanity.com/paper/2503.20925/) (2025)
- [All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inference](https://mlsanity.com/paper/2603.08498/) (2026)

## Abstract (arXiv)

Prototypical methods have recently gained a lot of attention due to their intrinsic interpretable nature, which is obtained through the prototypes. With growing use cases of model reuse and distillation, there is a need to also study transfer of interpretability from one model to another. We present Proto2Proto, a novel method to transfer interpretability of one prototypical part network to another via knowledge distillation. Our approach aims to add interpretability to the "dark" knowledge transferred from the teacher to the shallower student model. We propose two novel losses: "Global Explanation" loss and "Patch-Prototype Correspondence" loss to facilitate such a transfer. Global Explanation loss forces the student prototypes to be close to teacher prototypes, and Patch-Prototype Correspondence loss enforces the local representations of the student to be similar to that of the teacher. Further, we propose three novel metrics to evaluate the student's proximity to the teacher as measures of interpretability transfer in our settings. We qualitatively and quantitatively demonstrate the effectiveness of our method on CUB-200-2011 and Stanford Cars datasets. Our experiments show that the proposed method indeed achieves interpretability transfer from teacher to student while simultaneously exhibiting competitive performance.