SVM and ELM: Who Wins? Object Recognition with Deep Convolutional Features from ImageNet
This work addresses the problem of selecting effective classifiers for image recognition with deep features, but it is incremental as it compares existing methods on established benchmarks.
The study compared classifiers for object recognition using deep convolutional features from ImageNet, finding that extreme learning machines (ELMs) outperform support vector machines (SVMs) in cross-domain tasks, with kernel ELM achieving about 4% higher average accuracy.
Deep learning with a convolutional neural network (CNN) has been proved to be very effective in feature extraction and representation of images. For image classification problems, this work aim at finding which classifier is more competitive based on high-level deep features of images. In this report, we have discussed the nearest neighbor, support vector machines and extreme learning machines for image classification under deep convolutional activation feature representation. Specifically, we adopt the benchmark object recognition dataset from multiple sources with domain bias for evaluating different classifiers. The deep features of the object dataset are obtained by a well-trained CNN with five convolutional layers and three fully-connected layers on the challenging ImageNet. Experiments demonstrate that the ELMs outperform SVMs in cross-domain recognition tasks. In particular, state-of-the-art results are obtained by kernel ELM which outperforms SVMs with about 4% of the average accuracy. The features and codes are available in http://www.escience.cn/people/lei/index.html