Extracting an Explanatory Graph to Interpret a CNN.
IEEE transactions on pattern analysis and machine intelligence, pp. 1-1, 2020.
This paper introduces an explanatory graph representation to reveal object parts encoded inside convolutional layers of a CNN. Given a pre-trained CNN, each filter in a conv-layer usually represents a mixture of object parts. We develop a simple yet effective method to learn an explanatory graph, which automatically disentangles object pa...More
Get fulltext within 24h
Full Text (Upload PDF)
PPT (Upload PPT)