Menu
video thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Integrating domain knowledge for enhanced concept model explainability in Plant Disease classification

Published on 2024-05-3170 Views

Deep learning-based plant disease detection has seen promising advancements, particularly in its remarkable ability to identify diseases through digital images. Nevertheless, these systems’ opacity an

Related categories

Presentation

Integrating Domain Knowledge for Enhanced Concept Model Explainability in Plant Disease Classification00:00
Motivation00:17
Related wo00:58
Testing with Concept Activation Vectors (TCAV) - 101:41
Testing with Concept Activation Vectors (TCAV) - 202:11
Limitations of TCAV - 103:36
Limitations of TCAV - 204:12
Contributions04:33
Proposed Framework05:18
Tomato Disease Concepts Ontology - 106:50
Tomato Disease Concepts Ontology - 207:28
Synthetic Automatic Concepts Images Generation - 109:19
Synthetic Automatic Concepts Images Generation - 209:52
Synthetic Automatic Concepts Images Generation - 310:13
Experiments and results10:49
Results11:04
Conclusion12:07
Thank you13:27
Except where otherwise noted, content on this site is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International license.