Structured DropConnect for Uncertainty Inference in Image Classification

TL;DR

This paper introduces a structured DropConnect framework that models uncertainty in image classification by using a Dirichlet distribution, improving misclassification and out-of-distribution detection across different neural network architectures.

Contribution

The paper proposes a novel structured DropConnect method that models output uncertainty with a Dirichlet distribution, applicable to various network structures for improved inference.

Findings

Comparable performance to existing uncertainty methods

Effective in misclassification detection

Generalizes well across different network architectures

Abstract

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.