Faster ISNet for Background Bias Mitigation on Deep Neural Networks

Faster ISNet for Background Bias Mitigation on Deep Neural Networks

Bias or spurious correlations in image backgrounds can impact neural networks, causing shortcut learning (Clever Hans Effect) and hampering generalization to real-world data. ISNet, a recently introduced architecture, proposed the optimization of Layer-Wise Relevance Propagation (LRP, an explanation...

Full description

Bibliographic Details
Main Authors: Pedro R. A. S. Bassi, Sergio Decherchi, Andrea Cavalli
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Shortcut learning
layer-wise relevance propagation
COVID-19 detection
explainable artificial intelligence
background bias
ISNet
Online Access:https://ieeexplore.ieee.org/document/10681068/

Internet

https://ieeexplore.ieee.org/document/10681068/

Similar Items