# Sequentially Generated Instance-Dependent Image Representations for Classification

Source: [Sequentially Generated Instance-Dependent Image Representations for Classification](<https://www.sota2.com/research/paper/68fa61491e209131ce9f36c0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T19:55:35.464Z

Authors: Gabriel Dulac-Arnold, Ludovic Denoyer, Nicolas Thome, Matthieu Cord, Patrick Gallinari

Published: 2013-12-20T16:36:40.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1312.6594>)

[PDF](<https://arxiv.org/pdf/1312.6594.pdf>)