Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Sequentially Generated Instance-Dependent Image Representations for Classification
Matthieu Cord, patrick gallinari, Nicolas Thome, Ludovic Denoyer, Gabriel Dulac-Arnold
Dec 24, 2013 (modified: Dec 24, 2013)ICLR 2014 conference submissionreaders: everyone
Decision:submitted, no decision
Abstract:In this paper, we investigate a new framework for image classification that adaptively generates spatial representations. Our strategy is based on a sequential process that learns to explore the different regions of any image in order to infer its category. In particular, the choice of regions is specific to each image, directed by the actual content of previously selected regions.The capacity of the system to handle incomplete image information as well as its adaptive region selection allow the system to perform well in budgeted classification tasks by exploiting a dynamicly generated representation of each image. We demonstrate the system's abilities in a series of image-based exploration and classification tasks that highlight its learned exploration and inference abilities.
Enter your feedback below and we'll get back to you as soon as possible.