Sequentially Generated Instance-Dependent Image Representations for Classification
This work addresses the problem of efficient image classification for scenarios with limited computational resources, presenting an incremental improvement over existing methods.
The paper tackles image classification by adaptively generating spatial representations through a sequential region selection process, achieving strong performance in budgeted classification tasks.
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.