Deep Features for training Support Vector Machine

TL;DR

This paper presents a generic computer vision system that extracts and combines features from trained CNNs to improve image classification performance, achieving state-of-the-art results on a virus dataset.

Contribution

It introduces a method to extract, reduce dimensionality, and combine CNN features for SVM classification, enhancing performance across diverse datasets.

Findings

Significant performance boost over standard CNNs.

Effective feature combination improves classification accuracy.

Achieved state-of-the-art results on virus dataset.

Abstract

Features play a crucial role in computer vision. Initially designed to detect salient elements by means of handcrafted algorithms, features are now often learned by different layers in Convolutional Neural Networks (CNNs). This paper develops a generic computer vision system based on features extracted from trained CNNs. Multiple learned features are combined into a single structure to work on different image classification tasks. The proposed system was experimentally derived by testing several approaches for extracting features from the inner layers of CNNs and using them as inputs to SVMs that are then combined by sum rule. Dimensionality reduction techniques are used to reduce the high dimensionality of inner layers. The resulting vision system is shown to significantly boost the performance of standard CNNs across a large and diverse collection of image data sets. An ensemble of different topologies using the same approach obtains state-of-the-art results on a virus data set.