Multi-Attribute Vision Transformers are Efficient and Robust Learners
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| 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 |