Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
02 Feb 2019, Prathyush SPDeep Neural Networks (DNNs) excel on many complex perceptual tasks but it has proven notoriously difficult to understand how they reach their decisions. We here introduce a high-performance DNN architecture on ImageNet whose decisions are considerably easier to explain.
For more details, visit the source.