mlsanityData to 7 Oct 2026

This Looks Better than That: Better Interpretable Models with ProtoPNeXt

arXiv 2406.14675 ↗First posted 20 Jun 2024cs.CV cs.AI cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Prototypical-part models are a popular interpretable alternative to black-box deep learning models for computer vision. However, they are difficult to train, with high sensitivity to hyperparameter tuning, inhibiting their application to new datasets and our understanding of which methods truly improve their performance. To facilitate the careful study of prototypical-part networks (ProtoPNets), we create a new framework for integrating components of prototypical-part models -- ProtoPNeXt. Using ProtoPNeXt, we show that applying Bayesian hyperparameter tuning and an angular prototype similarity metric to the original ProtoPNet is sufficient to produce new state-of-the-art accuracy for prototypical-part models on CUB-200 across multiple backbones. We further deploy this framework to jointly optimize for accuracy and prototype interpretability as measured by metrics included in ProtoPNeXt. Using the same resources, this produces models with substantially superior semantics and changes in accuracy between +1.3% and -1.5%. The code and trained models will be made publicly available upon publication.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 22 of its 39 references that are in the map. First posted on arXiv 20 Jun 2024.

Builds on

22 of 39 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2015Spatial Transformer Networkscited by 1,423
  9. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  10. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  11. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  12. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 213
10 more
  1. 2016Synthesizing the preferred inputs for neurons in neural networks via deep generator networkscited by 181
  2. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 143
  3. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
  4. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
  5. 2021IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammographycited by 72
  6. 2023Learning Support and Trivial Prototypes for Interpretable Image Classificationcited by 38
  7. 2022Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networkscited by 37
  8. 2023This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizationscited by 36
  9. 2023ProtoSeg: Interpretable Semantic Segmentation with Prototypical Partscited by 33
  10. 2023ProtoExplorer: Interpretable Forensic Analysis of Deepfake Videos using Prototype Exploration and Refinementcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 1.

10 papers.

  1. 2025Interpretable and Testable Vision Features via Sparse Autoencoderscited by 24
  2. 2024Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?cited by 17
  3. 2025Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Timecited by 13
  4. 2025Formal Abductive Latent Explanations for Prototype-Based Networkscited by 5
  5. 2025On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNscited by 1
  6. 2025Comprehensive Evaluation of Prototype Neural Networkscited by 1
  7. 2025ProtoMask: Segmentation-Guided Prototype Learningcited by 0
  8. 2025What You See is (Usually) What You Get: Multimodal Prototype Networks that Abstain from Expensive Modalitiescited by 0
  9. 2025ProteinPNet: Prototypical Part Networks for Concept Learning in Spatial Proteomicscited by 0
  10. 2026Beyond L2: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architecturescited by 0