Evaluating the faithfulness of saliency maps in explaining deep learning models using realistic perturbations
Authors:
- José P. AmorimJAJosé P. Amorim
- Pedro H. AbreuPAPedro H. Abreu
- João SantosJSJoão Santos
- Marc CortesMCMarc Cortes
- Victor VilaVVVictor Vila
- 17 December 2022
- journal article
- research article
- Published by Elsevier in Information Processing & Management
- Vol. 60 (2)
Abstract
No abstract availableKeywords
This publication has 22 references indexed in Scilit:
- What Do Different Evaluation Metrics Tell Us About Saliency Models?IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast CancerJAMA, 2017
- Meaningful information and the right to explanationInternational Data Privacy Law, 2017
- A causal framework for explaining the predictions of black-box sequence-to-sequence models2017
- Evaluating the Visualization of What a Deep Neural Network Has LearnedIEEE Transactions on Neural Networks and Learning Systems, 2016
- Assessment of lymph node involvement in colorectal cancerWorld Journal of Gastrointestinal Surgery, 2016
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance PropagationPLOS ONE, 2015
- Visualizing and Understanding Convolutional Networks2014
- Saliency and Human Fixations: State-of-the-Art and Study of Comparison Metrics2013
- Pathology Issues Related to SN Procedures and Increased Detection of Micrometastases and Isolated Tumor CellsBreast Disease, 2010