43 datasets found

Microsoft COCO 2014 and 2017 datasets for object detection, segmentation, and captioning

The SEED dataset contains 15 subjects recorded while watching movie clips designated with a negative/neutral/positive emotion label.

A well-known dataset for object detection and image segmentation

Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature...

The Foggy Cityscapes dataset is an extension to the Cityscapes dataset, containing 5k diverse real-world urban driving scenes with fog.

The Caltech-UCSD Birds-200-2011 Dataset consists of 11,169 bird images from 200 categories and each category has 60 images averagely.

The MIT scene parsing dataset used for training the FCN network.

The proposed method for automatically generating image masks to train Mask R-CNN for object detection.

The MS COCO 2014 Dataset contains images of 91 object categories, which contains 82783 training images, 40504 validation images and 40775 testing images.

CamVid dataset is a benchmark dataset for semantic segmentation. It consists of 700 images with 11 object classes.

BDD100K Dataset is a large-scale dataset for autonomous driving, containing 100,000 images, with 20,000 images for training and 80,000 images for testing.

The dataset used in the paper is the Pascal VOC 2012 dataset, which is a benchmark for instance segmentation. The dataset consists of 1464 images with 20 class categories and...

COCO Stuff dataset is an extension of the COCO dataset, 164,000 images covering 171 classes are annotated with segmentation masks.

The Microsoft Common Objects in Context (COCO) dataset is a benchmark for object detection, segmentation, and image classification.

A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics.

The MS COCO dataset is a large benchmark for image captioning, containing 328K images with 5 caption descriptions each.

The COCO+LVIS dataset contains millions of high-quality labels for natural images.

G-Ref is a dataset for referring image segmentation, comprising 104K referring language expressions for around 55K objects in about 27K images.

The PASCAL Context dataset is a benchmark for multi-task learning in computer vision. It contains 10103 images with 5 tasks: semantic segmentation, human body part segmentation,...

A dataset for segment anything model (SAM) to evaluate its performance.