Multi-Attribute Vision Transformers are Efficient and Robust Learners

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gani, Hanan, Saadi, Nada, Hussein, Noor, Nandakumar, Karthik
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913437648420864
author Gani, Hanan
Saadi, Nada
Hussein, Noor
Nandakumar, Karthik
author_facet Gani, Hanan
Saadi, Nada
Hussein, Noor
Nandakumar, Karthik
contents Since their inception, Vision Transformers (ViTs) have emerged as a compelling alternative to Convolutional Neural Networks (CNNs) across a wide spectrum of tasks. ViTs exhibit notable characteristics, including global attention, resilience against occlusions, and adaptability to distribution shifts. One underexplored aspect of ViTs is their potential for multi-attribute learning, referring to their ability to simultaneously grasp multiple attribute-related tasks. In this paper, we delve into the multi-attribute learning capability of ViTs, presenting a straightforward yet effective strategy for training various attributes through a single ViT network as distinct tasks. We assess the resilience of multi-attribute ViTs against adversarial attacks and compare their performance against ViTs designed for single attributes. Moreover, we further evaluate the robustness of multi-attribute ViTs against a recent transformer based attack called Patch-Fool. Our empirical findings on the CelebA dataset provide validation for our assertion. Our code is available at https://github.com/hananshafi/MTL-ViT
format Preprint
id arxiv_https___arxiv_org_abs_2402_08070
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Attribute Vision Transformers are Efficient and Robust Learners
Gani, Hanan
Saadi, Nada
Hussein, Noor
Nandakumar, Karthik
Computer Vision and Pattern Recognition
Since their inception, Vision Transformers (ViTs) have emerged as a compelling alternative to Convolutional Neural Networks (CNNs) across a wide spectrum of tasks. ViTs exhibit notable characteristics, including global attention, resilience against occlusions, and adaptability to distribution shifts. One underexplored aspect of ViTs is their potential for multi-attribute learning, referring to their ability to simultaneously grasp multiple attribute-related tasks. In this paper, we delve into the multi-attribute learning capability of ViTs, presenting a straightforward yet effective strategy for training various attributes through a single ViT network as distinct tasks. We assess the resilience of multi-attribute ViTs against adversarial attacks and compare their performance against ViTs designed for single attributes. Moreover, we further evaluate the robustness of multi-attribute ViTs against a recent transformer based attack called Patch-Fool. Our empirical findings on the CelebA dataset provide validation for our assertion. Our code is available at https://github.com/hananshafi/MTL-ViT
title Multi-Attribute Vision Transformers are Efficient and Robust Learners
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.08070