← Back to all news
arXiv Computer Vision By Luisa Gall\'ee, Meinrad Beer, Michael G\"otz

Hierarchical Vision Transformer with Prototypes for Interpretable Medical Image Classification

Read the original on arXiv Computer Vision →

HierViT is a hierarchical Vision Transformer designed for medical image classification that balances strong predictive performance with interpretability. The model first predicts clinically relevant visual appearance attributes and then uses a hierarchical reasoning process to infer the final diagnosis. Attribute‑specific prototypes and attention maps are visualized to provide complementary views of the model’s reasoning, linking representative image examples and spatial attention to semantically defined visual features.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
5d ago

A Lightweight Attention-Based CNN with Saliency-Map Interpretability for Skin Cancer Detection

The paper introduces a lightweight attention-based CNN (CNN-Attention) for binary skin cancer classification that uses channel attention to highlight informative dermoscopic regions while keeping computational demands low. Trained on a dataset of 2,637 images, the model achieved 87 % accuracy, 0.9475 ROC AUC, and 0.9430 PR AUC, matching MobileNet’s performance with roughly half the parameters and storage. Saliency maps are employed to provide explainability by visualizing the image areas that influence predictions.

By Sanjana Islam Kasfia, Md. Ismiel Hossen Abir, AKM Bahalul Haque, Abir Mahmud Shahariar
safety
More like this →
arXiv AI
6d ago

SAP-ViT: A Self-Attributing Patch Vision Transformer for Medical Image Classification

SAP-ViT is a Vision Transformer that replaces the traditional global classification token with direct aggregation of last‑layer patch embeddings, enabling class predictions to be decomposed into patch‑level contributions during the forward pass. The model incorporates sparsity regularization to produce concise, readable evidence and introduces an input‑space back‑mapping mechanism to identify which input patches influence the output. Experiments on diverse medical imaging datasets show that SAP‑ViT retains strong classification performance while delivering consistent, interpretable patch‑level explanations, with ablation studies confirming the benefits of both sparsity and back‑mapping.

By Wei Zhang, Wolfgang Nejdl, Ming Tang
llmsragcomputer-visionefficiencybenchmarkssafety
More like this →