52 datasets found

A variant of CIFAR-100 dataset, where the original dataset is split into 20 disjoint tasks, each consisting of 2,500 samples from 5 classes.

Two datasets used for multi-task learning, CIFAR-100 and AGNews.

Deluge Networks are deep neural networks which efficiently facilitate massive cross-layer information inflows from preceding layers to succeeding layers.

The dataset used in the paper is CIFAR-10 and CIFAR-100, ImageNet, and their out-of-distribution variants.

The dataset used in the paper is a classification dataset, specifically CIFAR-10, CIFAR-100, TINY-IMAGENET, BASELINE, and PC-ANN.

The dataset used in the paper is a classification dataset, specifically CIFAR-100 and CUB200.

Federated learning (FL) is a paradigm where many clients collaboratively train a model under the coordination of a central server, while keeping the training data locally...

The dataset used in the WaveAttack paper, which consists of four classical benchmark datasets: CIFAR-10, CIFAR-100, GTSRB, and a subset of ImageNet.

The dataset used in the paper is a benchmark dataset for multi-class image classification: CIFAR-10, CIFAR-100, FashionMNIST, and SVHN.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the CIFAR-100 and ImageNet-R benchmarks for class-incremental continual...

A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations.

CIFAR-10, CIFAR-100, SVHN, MNIST, KMNIST, FashionMNIST

Long-tailed imbalance distribution is a common issue in practical computer vision applications.

The dataset used in the paper is CIFAR-10 and CIFAR-100, and ILSVRC-12.

The proposed DualConv is used to replace the standard convolution in VGG-16 and ResNet-50 to perform image classification experiments on CIFAR-10, CIFAR-100, and ImageNet datasets.

Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase.

The S-CIFAR-100 is constructed by splitting CIFAR-100 into 10 tasks where each one contains 10 classes and 6,000 images.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the CIFAR-100 and ImageNet-1k datasets for image classification and semantic...

Generative adversarial nets (GANs) are a class of deep learning models that consist of two neural networks: a generator and a discriminator.

CIFAR-100 and ILSVRC-2012 datasets used for training and testing the Zero Activation Predictor (ZAP) model.