Visualizing and Understanding Convolutional Networks

12 Nov 2013 Matthew D. Zeiler Rob Fergus

Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark. However there is no clear understanding of why they perform so well, or how they might be improved... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification ImageNet ZFNet (1 convnet, 512,1024,512 maps) Top 1 Accuracy 62.5% # 170
Top 5 Accuracy 84.0% # 111
Image Classification ImageNet ZFNet (ensemble, 6 convnets) Top 1 Accuracy 64% # 167
Top 5 Accuracy 85.3% # 108

Methods used in the Paper