Abstract
Large Convolutional Neural Network models have recently demonstrated impressive classification performance on the ImageNet benchmark \cite{Kriz12}. However there is no clear understanding of why they perform so well, or how they might be improved. In this paper we address both issues. We introduce a novel visualization technique that gives insight into the function of intermediate feature layers and the operation of the classifier. We also perform an ablation study to discover the performance contribution from different model layers. This enables us to find model architectures that outperform Krizhevsky \etal on the ImageNet classification benchmark. We show our ImageNet model generalizes well to other datasets: when the softmax classifier is retrained, it convincingly beats the current state-of-the-art results on Caltech-101 and Caltech-256 datasets.
Keywords
Softmax functionComputer scienceBenchmark (surveying)Convolutional neural networkClassifier (UML)Artificial intelligenceMachine learningVisualizationArtificial neural networkPattern recognition (psychology)
Related Publications
Visualizing and Understanding Convolutional Networks
Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark. However there is no clear understanding of why the...
ImageNet classification with deep convolutional neural networks
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On t...
AutoAugment: Learning Augmentation Strategies From Data
Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In ...
Factorized Bilinear Models for Image Recognition
Although Deep Convolutional Neural Networks (CNNs) have liberated their power in various computer vision tasks, the most important components of CNN, convolutional layers and fu...
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
The purpose of this study is to determine whether current video datasets have sufficient data for training very deep convolutional neural networks (CNNs) with spatio-temporal th...
Publication Info
- Year
- 2013
- Type
- article
- Citations
- 451
- Access
- Closed
External Links
Citation Metrics
451
OpenAlex
Cite This
Matthew D. Zeiler,
Rob Fergus
(2013).
Visualizing and Understanding Convolutional Neural Networks.
arXiv (Cornell University)
.