487 datasets found

Neuromorphic data understanding by CLIP and SNN

A conditional language generation model with Big Five Personality (BFP) feature vectors as input context, which writes human-like short texts.

A U-Net is trained to recover acoustic interference striations (AISs) from distorted ones. A random mode-coupling matrix model is introduced to generate a large number of...

Quantitative analysis of abnormalities in gynecologic cytopathology with deep learning

ExplainFix adopts two design principles: the “fixed filters” principle that all spatial filter weights of convolutional neural networks can be fixed at initialization and never...

The proposed rectified binary convolutional networks (RBCNs) are used to improve the performance of 1-bit DCNNs for mobile and AI chips based applications.

Deep learning on point clouds has received increased attention thanks to its wide applications in AR/VR and autonomous driving.

The proposed scheme uses IoT based health monitoring and CNN based object detection methods to detect social distancing violations and track exposed or infected people.

WCE curated colon disease dataset for deep learning

LSUN Church dataset is a large-scale image dataset containing 30,000 images of churches.

Deep unsupervised learning using nonequilibrium thermodynamics

Deep learning for decoding of linear codes - a syndrome-based approach

Error correction code transformer for decoding linear codes

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 is Occluded CIFAR.

The dataset used in the paper is Cluttered MNIST and CIFAR-10.

The CIFAR-10 dataset is used to evaluate the performance of FracBNN.

The ImageNet dataset is used to evaluate the performance of FracBNN.

The first convolutional layer is not binarized.

Binary neural networks (BNNs) have 1-bit weights and activations.