# Saliency-based Sequential Image Attention with Multiset Prediction

Source: [Saliency-based Sequential Image Attention with Multiset Prediction](<https://www.sota2.com/research/paper/68fa63d31e209131cea0105d>)

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

Data updated: 2025-10-25T20:50:10.530Z

Authors: Sean Welleck, Jialin Mao, Kyunghyun Cho, Zheng Zhang

Published: 2017-11-14T16:16:36.000Z

## Abstract

Humans process visual scenes selectively and sequentially using attention. Central to models of human visual attention is the saliency map. We propose a hierarchical visual architecture that operates on a saliency map and uses a novel attention mechanism to sequentially focus on salient regions and take additional glimpses within those regions. The architecture is motivated by human visual attention, and is used for multi-label image classification on a novel multiset task, demonstrating that it achieves high precision and recall while localizing objects with its attention. Unlike conventional multi-label image classification models, the model supports multiset prediction due to a reinforcement-learning based training process that allows for arbitrary label permutation and multiple instances per label.

## 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/1711.05165>)

[PDF](<https://arxiv.org/pdf/1711.05165.pdf>)