GRAPHIC interprets confusion matrices from linear classifiers on intermediate layers as graphs to visualize and quantify class confusion dynamics in deep learning.
For the image of the girl the initial labeling accuracy is 39%, the duplicate is labeled correctly with an accuracy of 23%
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning
GRAPHIC interprets confusion matrices from linear classifiers on intermediate layers as graphs to visualize and quantify class confusion dynamics in deep learning.