Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT

Understand

Latest results indicate that features learned via convolutional neural networks outperform previous descriptors on classification tasks by a large margin.

• It has been shown that these networks still work well when they are applied to datasets or recognition tasks different from those they were trained on.
• However, descriptors like SIFT are not only used in recognition but also for many correspondence problems that rely on descriptor matching.
• In this paper we compare features from various layers of convolutional neural nets to standard SIFT descriptors.