487 datasets found

Protein structures generated by Genie, a novel DDPM for de novo protein design

A new deep learning approach to learn a hierarchy of conditional latent variables that models a population of anatomical segmentations of interest, enables the classification of...

The conventional lottery ticket hypothesis (LTH) claims that there exists a sparse subnetwork within a dense neural network and a proper random initial-ization method called the...

DMLab-30 is a benchmark for multitask reinforcement learning in partially observable environments.

A dataset of 425,896 unique activation functions, created using the PANGAEA search space.

Three benchmark datasets: Act-Bench-CNN, Act-Bench-ResNet, and Act-Bench-ViT, created by training convolutional, residual, and vision transformer architectures from scratch with...

Brain MR dataset for tumor classification and source type classification

The eVED dataset is an extended and enriched version of the Vehicle Energy Dataset (VED), with accurate vehicle trip GPS coordinates and external information such as road speed...

CAwa-NeRF: Instant Learning of Compression-Aware NeRF Features

The dataset used in this paper is a collection of 25 state-of-the-art deep neural networks (DNNs) with different architectures and sizes.

CIFAR-10-S is a dataset that combines error-minimizing and One-Pixel Shortcut (OPS) to craft stronger imperceptible unlearnable examples.

One-Pixel Shortcut (OPS) is a data protection method that perturbs only one pixel in each image.

A multi-level ConvLSTM model for the automatic segmentation of left ventricle myocardium in infarcted porcine cine MR images

A deep learning based CAPTCHA solver for vulnerability assessment

A synthetic dataset for training a family of Reinforcement Learning (RL) methods to build explainable pathways for the differential diagnosis of anemia, as a primary use case.

Modern biomedical image analysis using deep learning often encounters the challenge of limited annotated data. To overcome this issue, deep generative models can be employed to...

The dataset used in the paper is not explicitly mentioned, but it is implied to be ImageNet and CIFAR-10/100.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used VGG-16, ResNet-50, and MobileNet-v2 models on the ImageNet and CIFAR-10...

The dataset used for training and testing deep neural networks-based denoising models for CT imaging.

The paper proposes a Bagging Deep Learning Training Framework (BEND) based on efficient neural network diffusion.