Image Classification with Consistent Supporting Evidence
Not on the map. Why?
Abstract (arXiv)
Adoption of machine learning models in healthcare requires end users' trust in the system. Models that provide additional supportive evidence for their predictions promise to facilitate adoption. We define consistent evidence to be both compatible and sufficient with respect to model predictions. We propose measures of model inconsistency and regularizers that promote more consistent evidence. We demonstrate our ideas in the context of edema severity grading from chest radiographs. We demonstrate empirically that consistent models provide competitive performance while supporting interpretation.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 13 Nov 2021.
Builds on
20 of 32 references.
References · 20
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2015Learning Deep Features for Discriminative Localizationcited by 2,430
- 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
- 2020Concept Bottleneck Modelscited by 1,022
- 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
- 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
- 2020Coherent Hierarchical Multi-Label Classification Networkscited by 65
- 2019A Logic-Driven Framework for Consistency of Neural Modelscited by 64
- 2019Interpretability Beyond Classification Output: Semantic Bottleneck Networkscited by 49
8 more
- 2016Rationale-Augmented Convolutional Neural Networks for Text Classificationcited by 39
- 2020Joint Modeling of Chest Radiographs and Radiology Reports for Pulmonary Edema Assessmentcited by 37
- 2018TED: Teaching AI to Explain its Decisionscited by 33
- 2018Semantic bottleneck for computer vision taskscited by 10
- 2020Deep Learning to Quantify Pulmonary Edema in Chest Radiographscited by 10
- 2021Learning to Predict with Supporting Evidence: Applications to Clinical Risk Predictioncited by 7
- 2019Semi-supervised Learning for Quantification of Pulmonary Edema in Chest X-Ray Imagescited by 2
- 2019Teaching AI to Explain its Decisions Using Embeddings and Multi-Task Learningcited by 1
Built on by
Citing papers per year: 2022: 2; 2023: 0; 2024: 0; 2025: 0; 2026: 1.
3 papers.