Abstract
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. 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)Classifier (UML)Artificial intelligenceConvolutional neural networkMachine learningVisualizationPattern recognition (psychology)
Affiliated Institutions
Related Publications
Visualizing and Understanding Convolutional Neural Networks
Large Convolutional Neural Network models have recently demonstrated impressive classification performance on the ImageNet benchmark \cite{Kriz12}. However there is no clear und...
Caltech-256 Object Category Dataset
We introduce a challenging set of 256 object categories containing a total of 30607 images. The original Caltech-101 [1] was collected by choosing a set of object categories, do...
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...
A systematic study of the class imbalance problem in convolutional neural networks
In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used meth...
Residual Dense Network for Image Super-Resolution
A very deep convolutional neural network (CNN) has recently achieved great success for image super-resolution (SR) and offered hierarchical features as well. However, most deep ...
Publication Info
- Year
- 2013
- Type
- preprint
- Citations
- 447
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
447
OpenAlex
Cite This
Matthew D. Zeiler,
Rob Fergus
(2013).
Visualizing and Understanding Convolutional Networks.
arXiv (Cornell University)
.
https://doi.org/10.48550/arxiv.1311.2901
Identifiers
- DOI
- 10.48550/arxiv.1311.2901