← Search

Jörn Hees

2 accepted papers

2018

What Do Deep Networks Like to See?

CVPR 2018poster

We propose a novel way to measure and understand convolutional neural networks by quantifying the amount of input signal they let in. To do this, an autoencoder (AE) was fine-tuned on gradients from a pre-trained classifier with fixed parameters. We compared the reconstructed samples from AEs that w…