Evaluating & enhancing deep learning systems via out-of-distribution detection
Deep Learning (DL) is continuously adopted in many industrial applications at a rapidly increasing pace. This includes safety- and security-critical applications where errors in the DL system can lead to massive or even fatal losses. With the rise of DL adoption, trustworthy AI initiatives have be...
Saved in:
Main Author: | Christopher, Berend David |
---|---|
Other Authors: | Liu Yang |
Format: | Thesis-Doctor of Philosophy |
Language: | English |
Published: |
Nanyang Technological University
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/162032 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Cats are not fish: Deep learning testing calls for out-of-distribution awareness
by: BEREND, David, et al.
Published: (2020) -
Evaluating variational autoencoder methods for out-of-distribution detection in autonomous vehicles
by: Dinh, Phuc Hung
Published: (2023) -
Computational imaging and detection via deep learning
by: Kong, Lingdong
Published: (2020) -
Towards out-of-distribution detection for object detection networks
by: Kanodia, Ritwik
Published: (2022) -
Visual saliency computation and quality evaluation via deep learning
by: Yang, Sheng
Published: (2021)