# ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition

arXiv: https://arxiv.org/abs/2208.10431 · HTML: https://mlsanity.com/paper/2208.10431/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 63 references that are in the map.
- First posted on arXiv 22 Aug 2022.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations](https://mlsanity.com/paper/2106.01548/) (2021)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/1710.00935/) (2017)
- [IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformers](https://mlsanity.com/paper/2106.12620/) (2021)
- [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.14862/) (2021)
- [Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes](https://mlsanity.com/paper/2111.15000/) (2021)

## Built on by (most cited first, 30 of 63)

- [Interpretable Image Classification with Adaptive Prototype-based Vision Transformers](https://mlsanity.com/paper/2410.20722/) (2024)
- [LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models](https://mlsanity.com/paper/2404.03118/) (2024)
- [On the Concept Trustworthiness in Concept Bottleneck Models](https://mlsanity.com/paper/2403.14349/) (2024)
- [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)
- [PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation](https://mlsanity.com/paper/2412.03177/) (2024)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [DCBM: Data-Efficient Visual Concept Bottleneck Models](https://mlsanity.com/paper/2412.11576/) (2024)
- [The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers](https://mlsanity.com/paper/2307.14517/) (2023)
- [A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis](https://mlsanity.com/paper/2311.04157/) (2023)
- [Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation](https://mlsanity.com/paper/2501.11309/) (2025)
- [Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis](https://mlsanity.com/paper/2501.09333/) (2025)
- [Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition](https://mlsanity.com/paper/2312.00092/) (2023)
- [Interpretable Image Classification via Non-parametric Part Prototype Learning](https://mlsanity.com/paper/2503.10247/) (2025)
- [Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement](https://mlsanity.com/paper/2311.15303/) (2023)
- [AudioProtoPNet: An interpretable deep learning model for bird sound classification](https://mlsanity.com/paper/2404.10420/) (2024)
- [GEMTrans: A General, Echocardiography-based, Multi-Level Transformer Framework for Cardiovascular Diagnosis](https://mlsanity.com/paper/2308.13217/) (2023)
- [A survey on Concept-based Approaches For Model Improvement](https://mlsanity.com/paper/2403.14566/) (2024)
- [ProtoS-ViT: Visual foundation models for sparse self-explainable classifications](https://mlsanity.com/paper/2406.10025/) (2024)
- [Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace](https://mlsanity.com/paper/2305.15775/) (2023)
- [PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck](https://mlsanity.com/paper/2403.05297/) (2024)
- [FOCUS: Fused Observation of Channels for Unveiling Spectra](https://mlsanity.com/paper/2507.14787/) (2025)
- [SASFormer: Transformers for Sparsely Annotated Semantic Segmentation](https://mlsanity.com/paper/2212.02019/) (2022)
- [MoViT: Memorizing Vision Transformers for Medical Image Analysis](https://mlsanity.com/paper/2303.15553/) (2023)
- [On the Evaluation Consistency of Attribution-based Explanations](https://mlsanity.com/paper/2407.19471/) (2024)
- [An Overview of Prototype Formulations for Interpretable Deep Learning](https://mlsanity.com/paper/2410.08925/) (2024)
- [Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning](https://mlsanity.com/paper/2403.07078/) (2024)
- [SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence](https://mlsanity.com/paper/2507.19321/) (2025)
- [Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment](https://mlsanity.com/paper/2603.17655/) (2026)
- [Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining](https://mlsanity.com/paper/2307.03887/) (2023)

## Abstract (arXiv)

Prototypical part network (ProtoPNet) has drawn wide attention and boosted many follow-up studies due to its self-explanatory property for explainable artificial intelligence (XAI). However, when directly applying ProtoPNet on vision transformer (ViT) backbones, learned prototypes have a "distraction" problem: they have a relatively high probability of being activated by the background and pay less attention to the foreground. The powerful capability of modeling long-term dependency makes the transformer-based ProtoPNet hard to focus on prototypical parts, thus severely impairing its inherent interpretability. This paper proposes prototypical part transformer (ProtoPFormer) for appropriately and effectively applying the prototype-based method with ViTs for interpretable image recognition. The proposed method introduces global and local prototypes for capturing and highlighting the representative holistic and partial features of targets according to the architectural characteristics of ViTs. The global prototypes are adopted to provide the global view of objects to guide local prototypes to concentrate on the foreground while eliminating the influence of the background. Afterwards, local prototypes are explicitly supervised to concentrate on their respective prototypical visual parts, increasing the overall interpretability. Extensive experiments demonstrate that our proposed global and local prototypes can mutually correct each other and jointly make final decisions, which faithfully and transparently reason the decision-making processes associatively from the whole and local perspectives, respectively. Moreover, ProtoPFormer consistently achieves superior performance and visualization results over the state-of-the-art (SOTA) prototype-based baselines. Our code has been released at https://github.com/zju-vipa/ProtoPFormer.