Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912498941165568 |
|---|---|
| author | Kleinmann, Marcel Agnihotri, Shashank Keuper, Margret |
| author_facet | Kleinmann, Marcel Agnihotri, Shashank Keuper, Margret |
| contents | Faithfulness and interpretability are essential for deploying deep neural networks (DNNs) in safety-critical domains such as medical imaging. B-cos networks offer a promising solution by replacing standard linear layers with a weight-input alignment mechanism, producing inherently interpretable, class-specific explanations without post-hoc methods. While maintaining diagnostic performance competitive with state-of-the-art DNNs, standard B-cos models suffer from severe aliasing artifacts in their explanation maps, making them unsuitable for clinical use where clarity is essential. In this work, we address these limitations by introducing anti-aliasing strategies using FLCPooling (FLC) and BlurPool (BP) to significantly improve explanation quality. Our experiments on chest X-ray datasets demonstrate that the modified $\text{B-cos}_\text{FLC}$ and $\text{B-cos}_\text{BP}$ preserve strong predictive performance while providing faithful and artifact-free explanations suitable for clinical application in multi-class and multi-label settings. Code available at: GitHub repository (url: https://github.com/mkleinma/B-cos-medical-paper). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16761 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks Kleinmann, Marcel Agnihotri, Shashank Keuper, Margret Computer Vision and Pattern Recognition Machine Learning Faithfulness and interpretability are essential for deploying deep neural networks (DNNs) in safety-critical domains such as medical imaging. B-cos networks offer a promising solution by replacing standard linear layers with a weight-input alignment mechanism, producing inherently interpretable, class-specific explanations without post-hoc methods. While maintaining diagnostic performance competitive with state-of-the-art DNNs, standard B-cos models suffer from severe aliasing artifacts in their explanation maps, making them unsuitable for clinical use where clarity is essential. In this work, we address these limitations by introducing anti-aliasing strategies using FLCPooling (FLC) and BlurPool (BP) to significantly improve explanation quality. Our experiments on chest X-ray datasets demonstrate that the modified $\text{B-cos}_\text{FLC}$ and $\text{B-cos}_\text{BP}$ preserve strong predictive performance while providing faithful and artifact-free explanations suitable for clinical application in multi-class and multi-label settings. Code available at: GitHub repository (url: https://github.com/mkleinma/B-cos-medical-paper). |
| title | Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2507.16761 |