ﻻ يوجد ملخص باللغة العربية
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.
Deep neural networks (DNNs) have achieved state-of-the-art performances in many important domains, including medical diagnosis, security, and autonomous driving. In these domains where safety is highly critical, an erroneous decision can result in se
Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the support set base
We propose to apply a 2D CNN architecture to 3D MRI image Alzheimers disease classification. Training a 3D convolutional neural network (CNN) is time-consuming and computationally expensive. We make use of approximate rank pooling to transform the 3D
In image classification, merging the opinion of several human experts is very important for different tasks such as the evaluation or the training. Indeed, the ground truth is rarely known before the scene imaging. We propose here different models in
Recent advances in self-attention and pure multi-layer perceptrons (MLP) models for vision have shown great potential in achieving promising performance with fewer inductive biases. These models are generally based on learning interaction among spati