Selected papers and possible corresponding codes for part-prototype-based papers for XAI.
If you find a paper missed in this repository, please feel free to pull a request here.
Prototype-based methods are inclined to achieve interpretable image classification, which dissect the image by finding prototypical parts, and combine evidence from the prototypes to make a final classification. Each prototype is a feature vector that corresponds to a specific part of the object. With these prototypes, these methods can explain the reasoning process of a deep model like human beings, and they achieve comparable or even better accuracy with their analogous non-interpretable counterpart.
-
Towards Interpretable Deep Reinforcement Learning with Human-Friendly Prototypes (ICLR 2023)
-
ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model (NIPS 2022)
-
Semi-ProtoPNet Deep Neural Network for the Classification of Defective Power Grid Distribution Structures (Sensors 2022)
-
Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models (MICCAI 2022)
-
ProtoPool: Interpretable Image Classification with Differentiable Prototypes Assignment (ECCV 2022)
-
ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder (ICML 2022)
-
Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes (CVPR 2022)
-
Proto2Proto: Can you recognize the car, the way I do? (CVPR 2022)
-
ProtGNN: Towards Self-Explaining Graph Neural Networks (AAAI 2022)
-
ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classification (ECML PKDD 2022)
-
ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition (Arxiv)
-
Concept-level Debugging of Part-Prototype Networks (Arxiv)
-
Extending explainability of generative classifiers with prototypical parts (Essay.Twente)
-
But that's not why: Inference adjustment by interactive prototype deselection (Arxiv)
-
Learnable Visual Words for Interpretable Image Recognition (Arxiv)
-
Multi-Grained Interpretable Network for Image Recognition
-
Neural Prototype Trees for Interpretable Fine-grained Image Recognition (CVPR 2021)
-
ProtoPShare: Prototypical Parts Sharing for Similarity Discovery in Interpretable Image Classification (KDD 2021)
-
Interpretable Image Recognition by Constructing Transparent Embedding Space (ICCV 2021)
-
These do not Look Like Those: An Interpretable Deep Learning Model for Image Recognition (IEEE Access)
-
Leveraging Class Hierarchies with Metric-Guided Prototype Learning (BMVC 2021)
-
This looks like that, because... explaining prototypes for interpretable image recognition (Arxiv)
-
This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks (Arxiv)
-
This Looks Like That: Deep Learning for Interpretable Image Recognition (NIPS 2019)
-
Interpretable Image Recognition with Hierarchical Prototypes (HCOMP 2019)