36 datasets found

The proposed method uses the MNIST and CIFAR10 datasets for fully-connected DNNs.

Convolution and self-attention are acting as two fundamental building blocks in deep neural networks, where the former extracts local image features in a linear way while the...

The proposed attack is based on transfer-based and score-based methods and is both gradient-free and query-efficient.

The dataset used in the paper to evaluate the alignment of deep neural networks with human perception.

Head and Neck PET-CT dataset from the Cancer Image Archive (TCIA) used for evaluating the proposed feature gradient flow method for interpreting deep neural networks in head and...

Tabular datasets for active learning on deep neural networks

Tabular datasets for active learning on deep neural networks

CirCNN is a neural network architecture that uses block-circulant matrices to reduce the number of parameters and computations.

Unitary group convolutions (UGConvs) are a building block for neural networks that combines a group convolution with unitary transforms in feature space.

Combining clustering and representation learning is one of the most promising approaches for unsupervised learning of deep neural networks.

A recommender system generates personalized recommendations for a user by computing the preference score of items, sorting the items according to the score, and filtering top-K...

The VGG-16 and ResNet-50 DNNs are used as victim DNNs in the attack.

The VGG and ResNet DNNs are used as victim DNNs in the attack.

The dataset used in this paper is a MobileNetV2 model, which is a type of deep neural network. The dataset is used to evaluate the performance of the proposed heterogeneous system.

Diabetic retinopathy (DR) is a leading cause of vision loss in the world and numerous cutting-edge works have built powerful deep neural networks (DNNs) to automatically...

The dataset used for training and validation of the proposed approach to combine semantic segmentation and dense outlier detection.