Neuroscope: An Explainable AI Toolbox for Semantic Segmentation and Image Classification of Convolutional Neural Nets

Autor: Fei Chen, Tim Dahmen, Christian Schorr, Payman Goodarzi
Jazyk: angličtina
Rok vydání: 2021
Předmět:
Interface (Java)
Computer science
02 engineering and technology
lcsh:Technology
explainable AI
lcsh:Chemistry
convolutional neural nets
0202 electrical engineering
electronic engineering
information engineering
General Materials Science
Segmentation
lcsh:QH301-705.5
Instrumentation
Graphical user interface
Fluid Flow and Transfer Processes
Artificial neural network
Contextual image classification
lcsh:T
business.industry
Process Chemistry and Technology
Deep learning
General Engineering
020207 software engineering
lcsh:QC1-999
Toolbox
semantic segmentation
Computer Science Applications
Visualization
lcsh:Biology (General)
lcsh:QD1-999
lcsh:TA1-2040
020201 artificial intelligence & image processing
Artificial intelligence
lcsh:Engineering (General). Civil engineering (General)
business
lcsh:Physics
image classification
Zdroj: Applied Sciences
Volume 11
Issue 5
Applied Sciences, Vol 11, Iss 2199, p 2199 (2021)
ISSN: 2076-3417
DOI: 10.3390/app11052199
Popis: Trust in artificial intelligence (AI) predictions is a crucial point for a widespread acceptance of new technologies, especially in sensitive areas like autonomous driving. The need for tools explaining AI for deep learning of images is thus eminent. Our proposed toolbox Neuroscope addresses this demand by offering state-of-the-art visualization algorithms for image classification and newly adapted methods for semantic segmentation of convolutional neural nets (CNNs). With its easy to use graphical user interface (GUI), it provides visualization on all layers of a CNN. Due to its open model-view-controller architecture, networks generated and trained with Keras and PyTorch are processable, with an interface allowing extension to additional frameworks. We demonstrate the explanation abilities provided by Neuroscope using the example of traffic scene analysis.
Databáze: OpenAIRE
Externí odkaz: