# Towards Robust Image Classification Using Sequential Attention Models

Source: [Towards Robust Image Classification Using Sequential Attention Models](<https://www.sota2.com/research/paper/68fa66cd1e209131cea126ea>)

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

Data updated: 2025-10-25T21:59:21.344Z

Authors: Daniel Zoran, Mike Chrzanowski, Po-Sen Huang, Sven Gowal, Alex Mott, Pushmeet Kohl

Published: 2019-12-04T17:58:20.000Z

## Abstract

In this paper we propose to augment a modern neural-network architecture with an attention model inspired by human perception. Specifically, we adversarially train and analyze a neural model incorporating a human inspired, visual attention component that is guided by a recurrent top-down sequential process. Our experimental evaluation uncovers several notable findings about the robustness and behavior of this new model. First, introducing attention to the model significantly improves adversarial robustness resulting in state-of-the-art ImageNet accuracies under a wide range of random targeted attack strengths. Second, we show that by varying the number of attention steps (glances/fixations) for which the model is unrolled, we are able to make its defense capabilities stronger, even in light of stronger attacks --- resulting in a "computational race" between the attacker and the defender. Finally, we show that some of the adversarial examples generated by attacking our model are quite different from conventional adversarial examples --- they contain global, salient and spatially coherent structures coming from the target class that would be recognizable even to a human, and work by distracting the attention of the model away from the main object in the original image.

## 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/1912.02184>)

[PDF](<https://arxiv.org/pdf/1912.02184.pdf>)