The DOI matches its Crossref record; 62 of the 64 references it cites were found in a registry or an index.
Neural Prototype Trees for Interpretable Fine-grained Image Recognition
Open accessAbstract
Prototype-based methods use interpretable representations to address the black-box nature of deep learning models, in contrast to post-hoc explanation methods that only approximate such models. We propose the Neural Prototype Tree (ProtoTree), an intrinsically interpretable deep learning method for fine-grained image recognition. ProtoTree combines prototype learning with decision trees, and thus results in a globally interpretable model by design. Additionally, ProtoTree can locally explain a single prediction by outlining a decision path through the tree. Each node in our binary tree contains a trainable prototypical part. The presence or absence of this learned prototype in an image determines the routing through a node. Decision making is therefore similar to human reasoning: Does the bird have a red throat? And an elongated beak? Then it’s a hummingbird! We tune the accuracy-interpretability trade-off using ensemble methods, pruning and binarizing. We apply pruning without sacrificing accuracy, resulting in a small tree with only 8 learned prototypes along a path to classify a bird from 200 species. An ensemble of 5 ProtoTrees achieves competitive accuracy on the CUB-200-2011 and Stanford Cars data sets. Code is available at github.com/M-Nauta/ProtoTree.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Hence, no manual formulation of prototypes or concepts is required.”
From Explainable AI in medical imaging: An overview for clinical practitioners – Beyond saliency-based XAI approaches (2023) · cites this paper as [62]
In the citing paper
“In this sense, ProtoTree (Neural Prototype Trees) [62] provides a local and global explanation utilizing a decision tree that is explainable by design.”
From Explainable AI in medical imaging: An overview for clinical practitioners – Beyond saliency-based XAI approaches (2023) · cites this paper as [62]
In the citing paper
“Its hierarchical structure is intended to increase interpretability and lead to more insights regarding clusters in the data by exploiting the positive and the negative reasoning process.”
From Explainable AI in medical imaging: An overview for clinical practitioners – Beyond saliency-based XAI approaches (2023) · cites this paper as [62]
In the citing paper
“No manual formulation of prototypes/ concepts is required”
From Explainable AI in medical imaging: An overview for clinical practitioners – Beyond saliency-based XAI approaches (2023) · cites this paper as [62]
In the citing paper
“Possibility of ambiguous result”
From Explainable AI in medical imaging: An overview for clinical practitioners – Beyond saliency-based XAI approaches (2023) · cites this paper as [62]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
(2010) · Cited by 14,134
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294
Recognition-by-components: A theory of human image understanding.
Biederman, I. (1987) · Psychological Review · doi:10.1037/0033-295x.94.2.115 · Cited by 5,621
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Flagged first, then by citations
2 of the 64 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- kindermans, 2019, The (Un)reliability of Saliency Methods, 267
- wah, 2011, The Caltech-UCSD Birds-200 - 2011 Dataset, Technical Report CNS-TR-2011-001
Cited by
Sorted by citations
Items 201–268 of 268
Wang, J., Wang, P., Feng, Y., Liu, H., Gao, C., & Jing, L. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680707 · Cited by 1
Text-Guided Feature Mining for Fine-Grained Ship Classification in Optical Remote Sensing Images
Liu, X., Wang, H., Yang, C., Yang, K., & Guan, N. (2024) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv63323.2024.10821549 · Cited by 1
Li, J., Yang, Y., Long, H., & Qiu, S. (2024) · International Conference on Information Systems and Computing Technology (ISCTech) · doi:10.1109/isctech63666.2024.10845546 · Cited by 1
Building Intrinsically Interpretable Deep Neural Networks: A Survey
Zhang, W., Jiao, L., & Pan, Q. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10865081 · Cited by 1
Pipvit: Patch-Based Visual Interpretable Prototypes for Retinal Image AnalysisPreprint
Oghbaie, M., Araújo, T., & Bogunović, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5336537 · Cited by 1
SONG: Self-Organizing Neural GraphsPreprint
Struski, Ł., Danel, T., Śmieja, M., Tabor, J., & Zieliński, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.13214
DRIB: Interpreting DNN with Dynamic Reasoning and Information Bottleneck
Si, Y., Cheng, K., Jiang, Z., Zhou, H., & Tahir, R. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-5194-7_14
SONGs: Self-Organizing Neural Graphs
Struski, Ł., Danel, T., Śmieja, M., Tabor, J., & Zieliński, B. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00384
An Interpretable Two-Layered Neural Network Structure–Based on Component-Wise Reasoning
Bakhtiari, M. M., & Villmann, T. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42505-9_13
Hawkeye: A PyTorch-based Library for Fine-Grained Image Recognition with Deep Learning
He, J., Shen, Y., Wei, X.-S., & Wu, Y. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3613461
Part-Aware Prototype-Aligned Interpretable Image Classification with Basic Feature Domain
Li, L., Gong, X., Wang, C., & Kong, W. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8391-9_15
Interactive Learning for Interpretable Visual Recognition via Semantic-Aware Self-Teaching Framework
Jiang, H., Li, H., Chen, J., Wan, W., & Wang, K. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8546-3_12
SCE: Shared Concept Extractor to Explain a CNN's Classification Dynamics
Kamakshi, V., & Krishnan, N. C. (2024) · Joint International Conference on Data Science & Management of Data (CODS-COMAD) · doi:10.1145/3632410.3632425
Wang, C., & Shen, X. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4690520
Enhancing Prototypical Space for Interpretable Image Classification
Baik, J. S., Yang, K. O., & Choi, J. W. (2023) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc58733.2023.10393495
UIPC-MF: User-Item Prototype Connection Matrix Factorization for Explainable Collaborative Filtering
Pan, L., & Soo, V. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2262-4_14
On the Interpretability and Explainability of Prototype-Based Methods and Reinforcement Learning
Davoudi, O. (2024) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2024-16083
Abstracting General Syntax for XAI after Decomposing Explanation Sub-ComponentsPreprint
Wormald, S. E., Maldaner, M. K., O'Connor, K., Dizon-Paradis, O. P., & Woodard, D. L. (2024) · Research Square · doi:10.21203/rs.3.rs-4824427/v1
Defining and Evaluating the Degrees of Abstraction in Explanations with Kolmogorov Complexity
Lemeire, J., & Buijsman, S. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-74650-5_3
EQ-CBM: A Probabilistic Concept Bottleneck with Energy-Based Models and Quantized Vectors
Kim, S., Ahn, D., Ko, B. C., Jang, I., & Kim, K. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0963-5_16
Prototype-Based Explanation for Semantic Gap Reduction With Distributional Embedding
Joo, H., Hong, S., Han, H., Yoon, Y., & Lee, J. (2025) · IEEE Access · doi:10.1109/access.2025.3535884
Kwon, H., Son, S., Morton, S. U., Wypij, D., Cleveland, J., Rollins, C. K., Huang, H., Goldmuntz, E., Panigrahy, A., Thomas, N. H., et al. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103538 · Cited by 1
TNIM: A Unified Text-to-Noise Influence Mapping Approach for Diffusion Models
Han, S. H., & Choi, H. (2025) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp64353.2025.00035
Einfache Darstellung von Komplexität
Cordier, M., Ditz, J. C., Heck, M., Lazar, V., & Müller, O. (2025) · Datenschutz und Datensicherheit - DuD · doi:10.1007/s11623-025-2081-8
How Were You Created? Explaining Synthetic Face Images Generated by Diffusion Models
Atote, B. S., & Sanchez, V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92089-9_17
Parallel Interpretation Network via Semantic Visual Probe and Counterfactual Verification
Wan, H., Cheng, K., & Zhou, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6576-1_6
Desirability vs. feasibility: a research through design inquiry of explainable AI
Corti, L., & Yang, J. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-340553-2.00010-1
CProtoNet: A conceptual prototype network based on conceptual similarity
Gao, L., Wang, S., Gu, W., Sun, Z., Xiao, J., Zhang, Y., & Wu, J. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06719-4
A Survey of Static and Temporal Explainable Methods and Their Applications in Knowledge Tracing
Li, F., Zhang, T., Yin, Y.-F., Fan, D., Yu, M., & Yu, G. (2025) · Journal of Computer Science and Technology · doi:10.1007/s11390-025-4239-0
Towards Balanced Representation Learning with Semantic Anchor Regularization
Wang, C., Nie, Q., Chen, Y., Li, J., Liu, Y., Jiang, X., Ge, Y., Wu, Y., Zheng, F., & Ma, L. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02519-y
Multidimensional Representation Dynamics for Abstract Visual Objects in Encoded Tangram Paradigms
Lian, Y., Pan, S., & Shi, L. (2025) · Brain Sciences · doi:10.3390/brainsci15090941
ProtoNAM: Prototypical Neural Additive Models for Interpretable Deep Tabular Learning
Xiong, G., Sinha, S., & Zhang, A. (2025) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3766072 · Cited by 1
Prototype-Guided Local Spatial Attention for Model Explanation
Yan, J., & Yamada, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04546-1_38
ExaM: Unsupervised Concept-Based Representation Learning to Better Explain Models in Vision Tasks
Héritier, M., Mekhazni, D., Leblond-Ménard, C., Godbout, B., Guilbaud, N., Alehdaghi, M., & Granger, É. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00259
Birds look like cars: adversarial analysis of intrinsically interpretable deep learning
Baniecki, H., & Biecek, P. (2025) · Machine Learning · doi:10.1007/s10994-025-06896-w
Enhancing Interpretability for Fine-Grained Vessel Recognition
Krywonos, W., & Cangelosi, A. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4097-6_22
Federated Adaptive Contrastive Prototype Learning for Heterogeneous Settings on Large-scale Data
Leng, T., Zhao, M., Zou, L., & Zhou, J. X. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229218
Huang, J., Guo, C., & Luk, W. (2025) · Information · doi:10.3390/info16121056
Hierarchical Concept Bottleneck With Compensation Concept Learning
Wang, C., Shang, M., Mao, K., Hong, X., Zhang, J., & Huang, X. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3645642
SVEBI: Towards the Interpretation and Explanation of Spiking Neural Networks
Laet, J. D., Behzadi-Khormouji, H., Deckers, L., & Jose Oramas, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06066-2_27
Machine Learning Models as Mathematics: Interpreting Explainable AI in Non-causal Terms
Buijsman, S. (2025) · Synthese Library/Synthese library · doi:10.1007/978-3-032-03083-2_8
Ragodos, R., Zhou, X., Wang, T., Pan, Y., & Luo, J. (2025) · ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL GIS) · doi:10.1145/3748636.3762719
Soares, L. A., Medeiros, M. V. S., & Díaz-Salazar, A. A. (2025) · ACM SIGKDD Explorations Newsletter · doi:10.1145/3787470.3787486
Explainable Image Classification Through Prototype-Based Feature Analysis and Mosaic Reconstruction
Toofani, A., Singh, L., & Paul, S. (2025) · International Conference on Information Systems and Computer Networks (ISCON) · doi:10.1109/iscon65210.2025.11341274
CausalProto-CLIP:Fine-Grained and Interpretable Vision-Language Modeling via Causal Prototypes
Meng, Y., Wei, Q., Pei, Z., Miao, P., Tan, C., & Meng, Z. (2025) · International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) · doi:10.1109/cei66465.2025.11398612
Interpretable crop pest and disease identification based on comparative concept tree
Jia, B., Zheng, Z., Zeng, J., Shi, L., Ge, H., & Song, C. (2026) · PLoS ONE · doi:10.1371/journal.pone.0343715
KG-XNN: Knowledge-Graph-Guided Explainable Neural Network for Image Classification
Jiang, Z. (2025) · International Conference on Power, Electrical Engineering, Electronics and Control (PEEEC) · doi:10.1109/peeec67807.2025.00015
MCPNet++: Interpretable Classification Models via Multi-Level Concept Prototypes
Wang, B.-S., Wang, C.-Y., & Chiu, W. T. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3680506
Learning a Single Compact Soft Tree with Iterative Updates of Sample Weights
Saiga, A., & Inokuchi, A. (2025) · International Conference on Machine Learning and Applications · doi:10.1109/icmla66185.2025.00054
Attention spatiale artificielle pour des modèles profonds interprétables de qualité embryonnaire
Gomez, T. (2022) · theses.fr (ABES) · doi:10.70675/514b0c84z06afz49a5z8759z40a696a1c6a3
Learn to Rank: Visual Attribution by Learning Importance Ranking
Schinagl, D., Fruhwirth-Reisinger, C., Prutsch, A., Schulter, S., & Possegger, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37592-6_20
Towards explainable and interpretable deep neural networks
Jeanneret, G. (2024) · theses.fr (ABES) · doi:10.70675/ed07566bze7a3z4daazb9d7z03fd028f66ce
ProtoIENet: An interpretable approach for medical image classification
Wang, X., Yu, J., Zhang, W., Zhu, Y. Y., Xia, M., Huang, X., Cui, Y., Guo, D., & Zhang, X. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113772
Dual-Level Prototype Learning for Composite Degraded Image Restoration
Wang, Z., Zhao, H., Yao, L., Peng, J., & Zhao, K. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01300
INSTANT: Inference-Aware Fast Feedforward Networks
Kilic, R. B., Yıldırım, K. S., & Iacca, G. (2026) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3815117
Blanchard, M., Ducottet, C., Muselet, D., & Delézay, O. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00523
Multi-objective Evolutionary Optimization of Imbalanced Fast Feedforward Networks
Kilic, R. B., Yıldırım, K. S., & Iacca, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-23604-3_23
Decoupled Prototype Network Based on Grassmann Manifold Orthogonal Projection
Li, Y., Li, S., Ma, Y., Yang, R., & Linag, M. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9507-5_20
PIP-PACA: An Interpretable Image Classification Framework via Prototype-Aware Clustering Attention
Jia, X., Li, Y., & Wang, Y. (2026) · Journal of Imaging · doi:10.3390/jimaging12070308
Zhou, H., Wang, J., & Sun, M. (2026) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001426400264
A Modular Framework for Brain Tumor Segmentation and Explainable-by-Design Classification from MRI
Miglionico, G. C., Ducange, P., Fazzolari, M., & Marcelloni, F. (2026) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz69877.2026.11626386
Neethu, C. T., Mary, L., & Thampi, L. L. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10768-4
A Configurable Framework for Quantifying and Comparing Interpretability Across ML Models and Methods
Özen, B. K., Waschulzik, T., & Knoll, A. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8080250
KeyExpand: A Global-Local Feature Fusion Network with Interpretability for Retinal Age PredictionPreprint
Feng, X., Lv, D., Wang, S., Li, W., Li, H., Shen, M., Lv, F., & Gao, H. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7386827
ProtoMappingNet: Interpretable Hierarchical Prototypes Through Relational Prototype Mappings
Park, J., Lim, J., Cha, S., & Kim, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37174-4_17
Wang, X., Zhang, W., Xiao, Z., Yu, J., Zhu, Y. Y., Huang, X., Xia, M., & Teng, Z. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111457
Set Classification with Probabilistic Learning Vector Quantization on the Grassmann Manifold
Mohammadi, M., Ghosh, S., & Güven, Ç. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729342
Metadata
- Authors
- Nauta, M., van Bree, R., & Seifert, C.
- Affiliations
- University of Twente (NL)
- University of Duisburg-Essen (DE)
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 14928-14938
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3108752471
- Cited by
- 269
- References
- 64
- Citations by year
- 2026: 28 · 2025: 69 · 2024: 69 · 2023: 70 · 2022: 24 · 2021: 8
- FWCI
- 19.75
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- University of Twente Research Information (submittedVersion, other-oa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- prototype learning, decision tree, explainable deep learning, fine-grained image classification, explainable AI, local explanations, accuracy-interpretability trade-off, tree pruning, ensemble methods, binarization, bird species classification, CUB-200-2011, Stanford Cars
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
