Sequentially Generated Instance-Dependent Image Representations for Classification
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.
Cite
Text
Dulac-Arnold et al. "Sequentially Generated Instance-Dependent Image Representations for Classification." International Conference on Learning Representations, 2014.Markdown
[Dulac-Arnold et al. "Sequentially Generated Instance-Dependent Image Representations for Classification." International Conference on Learning Representations, 2014.](https://mlanthology.org/iclr/2014/dulacarnold2014iclr-sequentially/)BibTeX
@inproceedings{dulacarnold2014iclr-sequentially,
title = {{Sequentially Generated Instance-Dependent Image Representations for Classification}},
author = {Dulac-Arnold, Gabriel and Denoyer, Ludovic and Thome, Nicolas and Cord, Matthieu and Gallinari, Patrick},
booktitle = {International Conference on Learning Representations},
year = {2014},
url = {https://mlanthology.org/iclr/2014/dulacarnold2014iclr-sequentially/}
}