Papers › Structured DropConnect for Uncertainty Inference in Image Classification

Structured DropConnect for Uncertainty Inference in Image Classification

16 Jun 2021arXiv:2106.08624archive 2025-07-28

Wenqing Zheng, Jiyang Xie, Weidong Liu, Zhanyu Ma

With the complexity of the network structure, uncertainty inference has become an important task to improve the classification accuracy for artificial intelligence systems. For image classification tasks, we propose a structured DropConnect (SDC) framework to model the output of a deep neural network by a Dirichlet distribution. We introduce a DropConnect strategy on weights in the fully connected layers during training. In test, we split the network into several sub-networks, and then model the Dirichlet distribution by match its moments with the mean and variance of the outputs of these sub-networks. The entropy of the estimated Dirichlet distribution is finally utilized for uncertainty inference. In this paper, this framework is implemented on LeNet$5$ and VGG$16$ models for misclassification detection and out-of-distribution detection on MNIST and CIFAR-$10$ datasets. Experimental results show that the performance of the proposed SDC can be comparable to other uncertainty inference methods. Furthermore, the SDC is adapted well to different network structures with certain generalization capabilities and research prospects.

PaperPDFCode

Code

PRIS-CV/Structured-DropConnect officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationImage ClassificationOut-of-Distribution Detectionimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DropConnect

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections