Loading [a11y]/accessibility-menu.js
Structured Dropconnect for Uncertainty Inference in Image Classification | IEEE Conference Publication | IEEE Xplore

Scheduled Maintenance: On Tuesday, May 20, IEEE Xplore will undergo scheduled maintenance from 1:00-5:00 PM ET (6:00-10:00 PM UTC). During this time, there may be intermittent impact on performance. We apologize for any inconvenience.

Structured Dropconnect for Uncertainty Inference in Image Classification


Abstract:

Uncertainty inference has become an important task to prove the reliability for deep neural networks. For image classification tasks, we propose a structured DropConnect ...Show More

Abstract:

Uncertainty inference has become an important task to prove the reliability for deep neural networks. For image classification tasks, we propose a structured DropConnect (SDC) framework to model the output of a deep neural network into a distribution. We introduce a DropConnect strategy in a structured manner in the fully connected layers, split the network into several sub-networks during testing, and choose the Dirichlet distribution to model the outputs of these sub-networks. The entropy of the parameterized Dirichlet distribution is finally utilized for uncertainty inference. In this paper, this framework is implemented on VGG16, and ResNet18 models for misclassification detection and open-set out-of-domain detection on CIFAR-10 and CIFAR-100 datasets. Experimental results show that the performance of the proposed SDC can be comparable to other uncertainty inference methods.
Date of Conference: 16-19 October 2022
Date Added to IEEE Xplore: 18 October 2022
ISBN Information:

ISSN Information:

Conference Location: Bordeaux, France

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.