Decomposing the Deep: Finding Class Specific Filters in Deep CNNs. (arXiv:2112.07719v2 [cs.CV] UPDATED)

Interpretability of Deep Neural Networks has become a major area of
exploration. Although these networks have achieved state of the art accuracy in
many tasks, it is extremely difficult to interpret and explain their decisions.
In this work we analyze the final and penultimate layers of Deep Convolutional
Networks and provide an efficient method for identifying subsets of features
that contribute most towards the network's decision for a class. We demonstrate
that the number of such features per class is …

arxiv cnns cv