In this paper we experimentally quantify the generality versus specificity of neurons in each layer of a deep convolutional neural network and report a few surprising results. Features must eventually transition from general to specific by the last layer of the network, but this transition has not been studied extensively. Such first-layer features appear not to be specific to a particular dataset or task, but general in that they are applicable to many datasets and tasks. Many deep neural networks trained on natural images exhibit a curious phenomenon in common: on the first layer they learn features similar to Gabor filters and color blobs. We hope that our recipe-style survey will serve as a guide, particularly for novice practitioners intending to use deep-learning techniques for computer vision. We start with “AlexNet” as our base CNN and then examine the broad variations proposed over time to suit different applications. We specifically consider one form of deep networks widely used in computer vision – convolutional neural networks (CNNs). Although general surveys of this fast-moving paradigm (i.e., deep-networks) exist, a survey specific to computer vision is missing. Therefore, it has become important to understand what kind of deep networks are suitable for a given problem. With this new paradigm, every problem in computer vision is now being re-examined from a deep learning perspective. However, of late, deep learning techniques have offered a compelling alternative – that of automatically learning problem-specific features. Traditional architectures for solving computer vision problems and the degree of success they enjoyed have been heavily reliant on hand-crafted features.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |