التفاصيل البيبلوغرافية
| العنوان: |
Combining pre-trained Vision Transformers and CIDER for Out Of Domain Detection |
| المؤلفون: |
Jouet, Grégor, Duhart, Clément, Rousseaux, Francis, Laborde, Julio, de Runz, Cyril |
| سنة النشر: |
2023 |
| المجموعة: |
Computer Science |
| مصطلحات موضوعية: |
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence |
| الوصف: |
Out-of-domain (OOD) detection is a crucial component in industrial applications as it helps identify when a model encounters inputs that are outside the training distribution. Most industrial pipelines rely on pre-trained models for downstream tasks such as CNN or Vision Transformers. This paper investigates the performance of those models on the task of out-of-domain detection. Our experiments demonstrate that pre-trained transformers models achieve higher detection performance out of the box. Furthermore, we show that pre-trained ViT and CNNs can be combined with refinement methods such as CIDER to improve their OOD detection performance even more. Our results suggest that transformers are a promising approach for OOD detection and set a stronger baseline for this task in many contexts |
| نوع الوثيقة: |
Working Paper |
| URL الوصول: |
http://arxiv.org/abs/2309.03047 |
| رقم الانضمام: |
edsarx.2309.03047 |
| قاعدة البيانات: |
arXiv |