Interpretable Deep

Interpretable deep learning aims to enhance the transparency and understandability of deep learning models, addressing the "black box" problem that hinders their adoption in high-stakes applications. Current research focuses on developing methods to improve the interpretability of existing deep neural networks (like CNNs and Transformers) across various domains, including image classification (e.g., facial expression recognition, medical image analysis) and time series forecasting, often incorporating techniques such as attention mechanisms and class activation mapping. This work is crucial for building trust and facilitating the responsible use of deep learning in fields like healthcare, finance, and other areas where understanding model decisions is paramount.

Papers

October 1, 2024

Spatial Action Unit Cues for Interpretable Deep Facial Expression Recognition
Soufiane Belharbi, Marco Pedersoli, Alessandro Lameiras Koerich, Simon Bacon, Eric Granger
Facial Expression Recognition Expression Recognition Class Activation Interpretable Classifier Interpretable Layer Action Cue Interpretable Deep

August 20, 2024

An Interpretable Deep Learning Approach for Morphological Script Type Analysis
Malamatenia Vlachou-Efstathiou, Ioannis Siglidis, Dominique Stutzmann, Mathieu Aubry
Morphological Analysis Interpretable Deep

February 1, 2024

Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues
Soufiane Belharbi, Marco Pedersoli, Alessandro Lameiras Koerich, Simon Bacon, Eric Granger
Facial Expression Recognition Expression Recognition Interpretable Deep Learning Interpretable Classifier Interpretable Layer Action Cue Interpretable Deep

January 22, 2024

Admission Prediction in Undergraduate Applications: an Interpretable Deep Learning Approach
Amisha Priyadarshini, Barbara Martinez-Neda, Sergio Gago-Masague
Deep Learning Based Learning Based Approach Interpretability Tool Interpretable Deep Undergraduate Admission Exam Reviewer Selection

December 17, 2023

An Interpretable Deep Learning Approach for Skin Cancer Categorization
Faysal Mahmud, Md. Mahin Mahfiz, Md. Zobayer Ibna Kabir, Yusha Abdullah
Explainable AI xAI Community Skin Cancer Classification Skin Cancer Detection Interpretable Deep

November 15, 2022

Explaining Cross-Domain Recognition with Interpretable Deep Classifier
Yiheng Zhang, Ting Yao, Zhaofan Qiu, Tao Mei
Deep Learning Domain Adaptation Unsupervised Domain Adaptation Interpretable Deep

June 1, 2022

Interpretable Deep Learning Classifier by Detection of Prototypical Parts on Kidney Stones Images
Daniel Flores-Araiza, Francisco Lopez-Tiro, Elias Villalvazo-Avila, Jonathan El-Beze, Jacques Hubert, Gilberto Ochoa-Ruiz, Christian Daul
Data Detection Prototypical Part Ex Vivo Kidney Stone Interpretable Deep Computer Aided Diagnosis System

May 12, 2022

Leveraging Uncertainty for Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images
Soufiane Belharbi, Jérôme Rony, Jose Dolz, Ismail Ben Ayed, Luke McCaffrey, Eric Granger
Segmentation Based Approach High Uncertainty Anticipation Histology Image Discriminative Region ROI Extraction Interpretable Deep

December 5, 2021

Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View
Di Jin, Elena Sergeeva, Wei-Hung Weng, Geeticka Chauhan, Peter Szolovits
Deep Learning Inherent Interpretability Data Driven Healthcare System Clinical Decision Support System Explainable Deep Learning Attribution Analysis Interpretable Deep

November 16, 2021

Online Advertising Revenue Forecasting: An Interpretable Deep Learning Approach
Max Würfel, Qiwei Han, Maximilian Kaiser
Deep Time Series Forecasting Interpretable Deep Online Advertising Revenue Ad Market