53 datasets found

Paucity of large curated hand-labeled training data for every domain-of-interest forms a major bottleneck in the deployment of machine learning models in computer vision and...

The Fashion-MNIST, CIFAR-10, and GTSRB datasets were used to evaluate differentiable logics for learning systems.

The dataset used in this paper is the MLPerf benchmark dataset.

A geometric multi-model fitting dataset

The proposed method for Object-agnostic State Classification (OaSC) combines structured knowledge on object states with visual information that relates the appearance of certain...

We create the long-tailed SVHN-LT dataset with maximally 1,000 images per class (head class), and vary ρ from 10 to 100 for different long-tailed versions.

We create the long-tailed CIFAR versions following [7,11] with controllable degrees of data imbalance, and keep the test set unchanged.

A novel active solubility sensing device using computer vision is proposed to improve separation purification performance and prevent malfunctions of separation equipment.

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

The CLAM dataset is a collection of whole slide images (WSIs) with corresponding attention maps.

A dataset for visually lossless content and motion adaptive shading

A dataset for the Falcor rendering framework

A dataset for perceptual model for adaptive local shading and refresh rate

A dataset for training and predicting visual error metrics for real-time applications

Lifelong-CIFAR10 and Lifelong-ImageNet are ever-expanding pools of test samples designed to enhance the robustness of current benchmarks by mitigating the issue of overfitting...

Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress

The Multi-Mice PartsTrack dataset is a challenging dataset for multi-mice part tracking in videos. It contains 10 videos of two or three mice interacting freely in a home cage...

Polynomial regression problem with naturally strong outliers. In such a setting a polynomial motion model for a moving scene is interpreted as the dominant scene motion stemming...

The MNIST and CIFAR datasets are used to test the robustness of neural networks against sparse attacks.

Compositional Zero-Shot Learning (CZSL) aims to predict unknown compositions made up of attribute and object pairs.