CIFAR-10
CIFAR-10 is a labeled dataset of 60,000 small color images sorted into 10 mutually exclusive object categories, with 6,000 images per class, used as a standard benchmark for image classification.
Computer Vision
Explore Computer Vision through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: Data & Datasets
Articles that also belong to these categories. Counts cover all of Computer Vision.
All articles (206)Deep Learning (53)Machine Learning (41)AI Models (39)Generative AI (37)AI Benchmarks (19)Multimodal AI (18)Neural Networks (17)Chinese AI (16)AI Companies (15)Meta AI (14)Robotics (14)Artificial Intelligence (13)Data & Datasets (13)Image Generation (13)AI Tools & Products (12)Open Source AI (12)Video Generation (11)Autonomous Vehicles (7)World Models (7)Natural Language Processing (6)People (6)AI Research (5)Model Architecture (5)Transformer Models (5)AI Hardware (4)Embodied AI (4)AI Ethics (3)AI Events (3)Developer Tools (3)Google (3)Model Evaluation (3)Training & Optimization (3)AI History (2)Google DeepMind (2)Healthcare AI (2)Interpretability (2)Large Language Models (2)AI Agents (1)AI for Science (1)Algorithms (1)Companies (1)Computer Science (1)Defense AI (1)Enterprise AI (1)Information Retrieval (1)Mathematics (1)Microsoft (1)NVIDIA (1)Physical AI (1)Robotics Companies (1)Statistics (1)
Showing 1-13 of 13 articles
COCO dataset
COCO (Common Objects in Context) is a large-scale dataset for object detection, image segmentation, keypoint detection, and image captioning.
Ego-Exo4D
Ego-Exo4D is a large-scale, multimodal, multiview video dataset and benchmark suite for computer vision research on skilled human activity, a central resource in egocentric vision.
Ego4D
Ego4D is a large-scale egocentric (first-person) video dataset and benchmark suite for computer vision, assembled by Meta AI (then Facebook AI Research) together with a consortium of 13 universities and labs…
Index (Figure AI)
Index is a proprietary data-collection program and mobile application operated by Figure AI.
LAION
LAION (Large-scale Artificial Intelligence Open Network) is a German non-profit organization
LVIS (Large Vocabulary Instance Segmentation)
LVIS (Large Vocabulary Instance Segmentation, pronounced "el-vis") is a large-scale instance segmentation benchmark for computer vision that targets the long-tailed regime of object detection.
MNIST
The Modified National Institute of Standards and Technology (MNIST) database is a collection of 70,000 grayscale images of handwritten digits (0 through 9) that has served as one of the most widely used…
Open Images
Open Images is a large annotated image dataset published by Google for computer vision research.
PASCAL VOC
PASCAL VOC (Pattern Analysis, Statistical Modelling and Computational Learning Visual Object Classes) is a long-running benchmark dataset and annual challenge for object recognition, object detection…
Project Aria
Project Aria is an egocentric data-collection research program run by Meta's Reality Labs Research. It was announced on September 16, 2020 .
Segment Anything Model and Dataset (SAM and SA-1B)
Segment Anything Model (SAM) is a promptable image segmentation foundation model released by Meta AI on April 5, 2023 that lets users "cut out" any object in an image with a single click, box, or mask prompt…
Visual question answering
Visual question answering (VQA) is the task of producing a natural-language answer to a natural-language question about an image.