Large-scale Learning with SVM and Convolutional for Generic Object Categorization

TLDR

Generic object recognition requires invariant features, and while convolutional networks learn such invariance, they are not optimal classifiers, whereas Support Vector Machines excel at classification but cannot learn complex invariances. The authors propose a hybrid system that trains a convolutional network for detection and recognition and then trains a Gaussian‑kernel SVM on the network’s learned features. They evaluate this system on a large generic object recognition task with six categories, each represented by multiple instances under varied poses, illuminations, and backgrounds. On a test set with unseen instances, the hybrid approach achieves a 5.9% error rate, outperforming the SVM alone (43.3%) and the convolutional net alone (7.2%).

Abstract

The detection and recognition of generic object categories with invariance to viewpoint, illumination, and clutter requires the combination of a feature extractor and a classifier. We show that architectures such as convolutional networks are good at learning invariant features, but not always optimal for classification, while Support Vector Machines are good at producing decision surfaces from wellbehaved feature vectors, but cannot learn complicated invariances. We present a hybrid system where a convolutional network is trained to detect and recognize generic objects, and a Gaussian-kernel SVM is trained from the features learned by the convolutional network. Results are given on a large generic object recognition task with six categories (human figures, four-legged animals, airplanes, trucks, cars, and "none of the above"), with multiple instances of each object category under various poses, illuminations, and backgrounds. On the test set, which contains different object instances than the training set, an SVM alone yields a 43.3% error rate, a convolutional net alone yields 7.2% and an SVM on top of features produced by the convolutional net yields 5.9%.