-
VAEs in the Presence of Missing Data
Real world datasets often contain entries with missing elements e.g. in a medical dataset, a patient is unlikely to have taken all possible diagnostic tests. -
DEMYSTIFYING CLIP DATA
Contrastive Language-Image Pre-training (CLIP) is an approach that has advanced research and applications in computer vision, fueling modern recognition systems and generative... -
RealBlur Test Dataset
The RealBlur test dataset for image deblurring. -
HIDE Test Dataset
The HIDE test dataset for image deblurring. -
GoPro Test Dataset
The GoPro test dataset for image deblurring. -
Arbitrary Bit-Width Network: A Joint Layer-Wise Quantization and Adaptive Inf...
Arbitrary bit-width network: A joint layer-wise quantization and adaptive inference approach. -
Mixed-precision Neural Network Quantization via Learned Layer-wise Importance
Mixed-precision neural network quantization via learned layer-wise importance. -
LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and...
The dataset used in the paper is not explicitly described. However, it is mentioned that the authors used a range of datasets, including CIFAR-10, GTSRB, Google Speech Command,... -
ObjectCompose
ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes -
MNIST Database
The MNIST database of handwritten digits is a popular benchmark data set for classification algorithms. -
DTU MVS Dataset and Local Light Field Fusion Dataset
The DTU MVS Dataset and the Local Light Field Fusion Dataset are used to evaluate the performance of the proposed GARF model. -
Office-Home, Office-31, and DomainNet
Office-Home, Office-31, and DomainNet are benchmark datasets for semi-supervised domain adaptation. -
Compositional Diffusion-Based Continuous Constraint Solvers
The dataset for 2D triangle packing, 2D shape arrangement with qualitative constraints, 3D object stacking with stability constraints, and 3D object packing with robots. -
Segment Anything Model
The dataset used in this paper is the Meta Research's Segment Anything Model (SAM) dataset, which consists of images. -
RotNIST dataset
RotNIST dataset -
ScanNet Dataset
The ScanNet dataset is a large-scale indoor dataset composed of monocular sequences with ground truth poses and depth images. -
CIFAR-10, STL-10, and ImageNet
The dataset used in the paper is CIFAR-10, STL-10, and ImageNet. -
Joint Prediction of Monocular Depth and Structure using Planar and Parallax G...
The dataset used in the paper is the KITTI Vision Benchmark and Cityscapes dataset for monocular depth estimation and structure prediction.
