# Is Attentional Channel Processing Design Required? Comprehensive Analysis Of Robustness Between Vision Transformers And Fully Attentional Networks

Source: [Is Attentional Channel Processing Design Required? Comprehensive Analysis Of Robustness Between Vision Transformers And Fully Attentional Networks](<https://www.sota2.com/research/paper/68fa6fbc1e209131cea47208>)

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

Data updated: 2025-10-26T01:25:24.907Z

Authors: Abhishri Ajit Medewar, Swanand Ashokrao Kavitkar

Published: 2023-06-08T18:33:12.000Z

## Abstract

The robustness testing has been performed for standard CNN models and Vision Transformers, however there is a lack of comprehensive study between the robustness of traditional Vision Transformers without an extra attentional channel design and the latest fully attentional network(FAN) models. So in this paper, we use the ImageNet dataset to compare the robustness of fully attentional network(FAN) models with traditional Vision Transformers to understand the role of an attentional channel processing design using white box attacks and also study the transferability between the same using black box attacks.

## 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/2306.05495>)

[PDF](<https://arxiv.org/pdf/2306.05495.pdf>)