CAManim: Animating end-to-end network activation maps.

Autor: Kaczmarek E; Children's Hospital of Eastern Ontario Research Institute, Ottawa, Canada., Miguel OX; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, Canada., Bowie AC; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, Canada., Ducharme R; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, Canada., Dingwall-Harvey ALJ; Children's Hospital of Eastern Ontario Research Institute, Ottawa, Canada.; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, Canada., Hawken S; Children's Hospital of Eastern Ontario Research Institute, Ottawa, Canada.; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, Canada.; School of Epidemiology and Public Health, University of Ottawa, Ottawa, Canada.; ICES, Toronto, Canada., Armour CM; Children's Hospital of Eastern Ontario Research Institute, Ottawa, Canada.; Department of Pediatrics, University of Ottawa, Ottawa, Canada.; Prenatal Screening Ontario, Better Outcomes Registry & Network, Ottawa, Canada., Walker MC; Children's Hospital of Eastern Ontario Research Institute, Ottawa, Canada.; Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, Canada.; School of Epidemiology and Public Health, University of Ottawa, Ottawa, Canada.; ICES, Toronto, Canada.; Department of Obstetrics and Gynecology, University of Ottawa, Ottawa, Canada.; International and Global Health Office, University of Ottawa, Ottawa, Canada.; BORN Ontario, Children's Hospital of Eastern Ontario, Ottawa, Canada.; Department of Obstetrics, Gynecology & Newborn Care, The Ottawa Hospital, Ottawa, Canada., Dick K; Children's Hospital of Eastern Ontario Research Institute, Ottawa, Canada.; Prenatal Screening Ontario, Better Outcomes Registry & Network, Ottawa, Canada.; BORN Ontario, Children's Hospital of Eastern Ontario, Ottawa, Canada.
Jazyk: angličtina
Zdroj: PloS one [PLoS One] 2024 Jun 18; Vol. 19 (6), pp. e0296985. Date of Electronic Publication: 2024 Jun 18 (Print Publication: 2024).
DOI: 10.1371/journal.pone.0296985
Abstrakt: Deep neural networks have been widely adopted in numerous domains due to their high performance and accessibility to developers and application-specific end-users. Fundamental to image-based applications is the development of Convolutional Neural Networks (CNNs), which possess the ability to automatically extract features from data. However, comprehending these complex models and their learned representations, which typically comprise millions of parameters and numerous layers, remains a challenge for both developers and end-users. This challenge arises due to the absence of interpretable and transparent tools to make sense of black-box models. There exists a growing body of Explainable Artificial Intelligence (XAI) literature, including a collection of methods denoted Class Activation Maps (CAMs), that seek to demystify what representations the model learns from the data, how it informs a given prediction, and why it, at times, performs poorly in certain tasks. We propose a novel XAI visualization method denoted CAManim that seeks to simultaneously broaden and focus end-user understanding of CNN predictions by animating the CAM-based network activation maps through all layers, effectively depicting from end-to-end how a model progressively arrives at the final layer activation. Herein, we demonstrate that CAManim works with any CAM-based method and various CNN architectures. Beyond qualitative model assessments, we additionally propose a novel quantitative assessment that expands upon the Remove and Debias (ROAD) metric, pairing the qualitative end-to-end network visual explanations assessment with our novel quantitative "yellow brick ROAD" assessment (ybROAD). This builds upon prior research to address the increasing demand for interpretable, robust, and transparent model assessment methodology, ultimately improving an end-user's trust in a given model's predictions. Examples and source code can be found at: https://omni-ml.github.io/pytorch-grad-cam-anim/.
Competing Interests: The authors have declared that no competing interests exist.
(Copyright: © 2024 Kaczmarek et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje