How certain are tansformers in image classification: uncertainty analysis with Monte Carlo dropout

Md. Farhadul Islam; Sarah Zabeen; Md. Azharul Islam; Fardin Bin Rahman; Anushua Ahmed; Dewan Ziaul Karim; Annajiat Alim Rasel; Meem Arafat Manab

doi:10.1117/12.2679442

7 June 2023 How certain are tansformers in image classification: uncertainty analysis with Monte Carlo dropout

Md. Farhadul Islam, Sarah Zabeen, Md. Azharul Islam, Fardin Bin Rahman, Anushua Ahmed, Dewan Ziaul Karim, Annajiat Alim Rasel, Meem Arafat Manab

Author Affiliations +

Proceedings Volume 12701, Fifteenth International Conference on Machine Vision (ICMV 2022); 127010K (2023) https://doi.org/10.1117/12.2679442
Event: Fifteenth International Conference on Machine Vision (ICMV 2022), 2022, Rome, Italy

Abstract

Researchers have been inspired to implement transformer models in solving machine vision problems after their tremendous success with natural language tasks. Using the straightforward architecture and swift performance of transformers, a variety of computer vision problems can be solved with more ease and effectiveness. However, a comparative evaluation of their uncertainty in prediction has not been done yet. As we know, real world applications require a measure of uncertainty to produce accurate predictions, which allows researchers to handle uncertain inputs and special cases, in order to successfully prevent overfitting. Our study approaches the unexplored issue of uncertainty estimation among three popular and effective transformer models employed in computer vision, such as Vision Transformers (ViT), Swin Transformers (SWT), and Compact Convolutional Transformers (CCT). We conduct a comparative experiment to determine which particular architecture is the most reliable in image classification. We use dropouts at the inference phase in order to measure the uncertainty of these transformer models. This approach, commonly known as Monte Carlo Dropout (MCD), works well as a low-complexity estimation to compute uncertainty. The MCD-based CCT model is the least uncertain architecture in this classification task. Our proposed MCD-infused CCT model also yields the best results with 78.4% accuracy, while the SWT model with embedded MCD exhibits Pmaximum performance gain where the accuracy increased by almost 3% with the final result being 71.4%.

Citation Download Citation

Md. Farhadul Islam, Sarah Zabeen, Md. Azharul Islam, Fardin Bin Rahman, Anushua Ahmed, Dewan Ziaul Karim, Annajiat Alim Rasel, and Meem Arafat Manab "How certain are tansformers in image classification: uncertainty analysis with Monte Carlo dropout", Proc. SPIE 12701, Fifteenth International Conference on Machine Vision (ICMV 2022), 127010K (7 June 2023); https://doi.org/10.1117/12.2679442

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Transformers

Monte Carlo methods

Performance modeling

Statistical modeling

Image classification

Artificial neural networks

Deep learning

Show All Keywords

Keywords/Phrases

Search In:

Publication Years