Visualizing and Understanding Convolutional Networks (2013-11-12T00:00:00.000000Z)

TL;DR

A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.

Abstract

Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark Krizhevsky et al. [18]. However there is no clear understanding of why they perform so well, or how they might be improved. In this paper we explore both issues. We introduce a novel visualization technique that gives insight into the function of intermediate feature layers and the operation of the classifier. Used in a diagnostic role, these visualizations allow us to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark. We also perform an ablation study to discover the performance contribution from different model layers. 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.

Authors

R. Fergus

8 papers

Matthew D. Zeiler

1 papers

TL;DR

Abstract

Authors

References32 items

Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks

Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Some Improvements on Deep Convolutional Neural Network Based Image Classification

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

Multipath Sparse Coding Using Hierarchical Matching Pursuit

ImageNet classification with deep convolutional neural networks

Multi-column deep neural network for traffic sign classification

Improving neural networks by preventing co-adaptation of feature detectors

Multi-column deep neural networks for image classification

Adaptive deconvolutional networks for mid and high level feature learning

Efficient learning of sparse, distributed, convolutional feature representations for object recognition

Unbiased look at dataset bias

Tiled convolutional neural networks

What is the best multi-stage architecture for object recognition?

Linear spatial pyramid matching using sparse coding for image classification

ImageNet: A large-scale hierarchical image database

Co-occurrence Histograms of Oriented Gradients for Pedestrian Detection

Extracting and composing robust features with denoising autoencoders

Greedy Layer-Wise Training of Deep Networks

On the Analysis and Interpretation of Inhomogeneous Quadratic Forms as Receptive Fields

A Fast Learning Algorithm for Deep Belief Nets

One-shot learning of object categories

Backpropagation Applied to Handwritten Zip Code Recognition

Visualizing and Understanding Convolutional Networks

Improving Histograms of Oriented Gradients for Pedestrian Detection

Classifi - cation entry

Generalized hierarchical matching for sub-category aware object classiﬁcation

Hybrid coding for selective search. In PASCAL VOC Classification Challenge

Visualizing Higher-Layer Features of a Deep Network

The caltech 256

Clarifai (2013), http://www.image-net.org/challenges/LSVRC/2013/ results

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names