Face attribute classification with evidential deep learning

Zeyneloğlu, Mehmet Arın and Ahmed, Sara Atito Ali and Yanıkoğlu, Berrin (2023) Face attribute classification with evidential deep learning. In: 15th International Conference on Machine Vision (ICMV 2022), Rome, Italy

[thumbnail of 127011M.pdf] PDF
Restricted to Registered users only

Download (3MB) | Request a copy


We address the problem of uncertainty quantification in the domain of face attribute classification, using Evidential Deep Learning (EDL) framework. The proposed EDL approach leverages the strength of Convolution Neural Networks (CNN), with the objective of representing the uncertainty in the output predictions. Predominantly, the softmax/sigmoid activation functions are applied to map the output logits of the CNN to target class probabilities in multi-class classification problems. By replacing the standard softmax/sigmoid output of a CNN with the parameters of the evidential distribution, EDL learns to represent the uncertainty in its predictions. The proposed approach is evaluated on CelebA and LFWA datasets. The quantitative and qualitative analysis demonstrate the suitability and strength of EDL to estimate the uncer- tainty in the output predictions without hindering the accuracy of CNN-based models.
Item Type: Papers in Conference Proceedings
Subjects: Q Science > QA Mathematics > QA076 Computer software
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Computer Science & Eng.
Faculty of Engineering and Natural Sciences
Depositing User: Berrin Yanıkoğlu
Date Deposited: 03 Oct 2023 22:10
Last Modified: 07 Feb 2024 10:21
URI: https://research.sabanciuniv.edu/id/eprint/48282

Actions (login required)

View Item
View Item