.png){kind=icon}
Return
EM-SEC: Efficient Multi-head Set-Valued Evidential Classification
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-05981-9_16.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In machine learning and deep learning, uncertainty quantification helps to accurately assess a model's confidence in its predictions, enabling the rejection of uncertain outcomes in safety-critical applications. However, in scenarios involving AI-assisted decision-making, proposing multiple plausible decisions can be more beneficial than either not making any decisions or risking incorrect ones. Set-valued classification is a relaxation of standard multiclass classification where, in cases of uncertainty, the classifier returns a set of potential labels instead of a single label. Current methods for set-valued classification often suffer from high computational complexity or fail to adequately quantify uncertainty. In this paper, we introduce a novel, computationally efficient approach to set-valued classification leveraging evidential deep learning and subjective logic, explicitly providing a measure of classification uncertainty. Our method employs a dual-head architecture: one head conducts multiclass evidential classification, while the other suggests candidate label sets when uncertainty is high. The proposed approach has linear worst-case computational complexity with respect to the number of classes. Extensive evaluation on several benchmark datasets demonstrates that our method showcases comparable performance to baseline set-valued methods, while being up to 23 times faster at inference on the benchmark datasets.
Keywords:
set-valued classification
evidential deep learning
subjective logic
utility maximization
uncertainty quantification
Journal
M
IF:
0
Papers:
28
Citations:
0
Organization
Cited Papers
ShareSave
A review of uncertainty quantification in deep learning: Techniques, applications and challenges.png)
INFORMATION FUSION
OAAI
INFORMATION FUSIONIF15.5
OAAIShareSaveShareSaveShareSaveShareSave
View more