75 datasets found

The dataset used in this paper is a collection of images of faces, each with a different expression.

The dataset used in the paper for 2D image classification, including MNIST, SVHN, USPS, and CIFAR-10 datasets.

The proposed scale-steerable CNN framework is validated on the MNIST-Scale and FMNIST-Scale datasets, which contain global scale variations. Additionally, a synthesized dataset,...

Pooling is a simple but widely used layer in modern deep CNN architectures for feature aggregation and extraction. Typical CNN design focuses on the conv layers and activation...

MERCURY accelerates DNN training by exploiting input similarity.

A comprehensive dataset featuring ten distinct hen breeds, capturing unique characteristics and traits of each breed.

ShiftAddViT: A hardware-inspired multiplication-reduced Vision Transformer model.

Hyperparameter optimization for transfer Convolutional Neural Networks (CNN) using Genetic Algorithm

The dataset used in the paper is a collection of point clouds with spinor features, where each point cloud is associated with a spinor feature and a regression target.

A deep learning and IoT based computer vision system to process computer vision and natural language in real time in order to address the safety and security of production sites...

The dataset used in the paper to prove the representation defects of a cascaded convolutional decoder network in frequency representation.

Deep convolutional neural networks have dominated the pattern recognition scene by providing much more accurate solutions in computer vision problems such as object recognition...

This dataset is used to evaluate CNNs and human observers on images with a texture-shape cue conflict.

Binary neural networks have attracted numerous attention in recent years. However, mainly due to the information loss stemming from the biased binarization, how to preserve the...

The proposed framework generates a unique set of context-dependent filters based on the input image, and combines them with max-pooling to produce transformation-invariant...

The paper proposes a decomposition of the convolutional filters over joint steerable bases across the space and the group geometry simultaneously, namely a rotation-equivariant...

Deep convolutional neural networks have recently proven extremely competitive in challenging image recognition tasks. This paper proposes the epitomic convolution as a new...

The dataset used in the paper is a large-scale comparison of pretrained models across computer vision tasks.

The dataset used for training and testing the proposed method.

The DenseNet dataset is a dataset for image recognition on handwritten digits composed of 60,000 training data and 10,000 test images.