Visualizing Convolutional Networks
Zeiler and Fergus visualized CNN layers with deconvolution, revealing edges, textures and objects emerging layer by layer inside the network.
2 reports · 2013–2016
What is actually happening inside a trained network, and how we can tell.
Zeiler and Fergus visualized CNN layers with deconvolution, revealing edges, textures and objects emerging layer by layer inside the network.
Grad-CAM explains CNN decisions with gradient-weighted heatmaps, revealing which image regions drove each prediction without retraining.