Learning interpretable concept groups in CNNs
We propose a novel training methodology---Concept Group Learning (CGL)---that encourages training of interpretable CNN filters by partitioning filters in each layer into concept groups, each of which is trained to learn a single visual concept. We achieve this through a novel regularization strategy...
Saved in:
Main Authors: | VARSHNEYA, Saurabh, LEDENT, Antoine, VANDERMEULEN, Rob, LEI, Yunwen, ENDERS, Matthias, BORTH, Damian, KLOFT, Marius |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7206 https://ink.library.smu.edu.sg/context/sis_research/article/8209/viewcontent/Interpretable_CNNs.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Improved generalisation bounds for deep learning through L∞ covering numbers
by: LEDENT, Antoine, et al.
Published: (2019) -
Interpretable tensor fusion
by: VARSHNEYA, Saurabh, et al.
Published: (2024) -
Sharper generalisation bounds for pairwise learning
by: LEI, Yunwen, et al.
Published: (2020) -
Fine-grained generalization analysis of inductive matrix completion
by: LEDENT, Antoine, et al.
Published: (2021) -
Fine-grained analysis of structured output prediction
by: MUSTAFA, Waleed, et al.
Published: (2021)