30 datasets found

The proposed approach is demonstrated on multiple vision tasks and modalities through a variety of applications.

The dataset used in the paper is a subset of the Caltech Silhouettes database, consisting of 11 images with 42 to 59 pixels in each class.

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

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 COCO 2014 validation set is used for evaluating the performance of the proposed method.

The MS COCO dataset is a task 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.

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.

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

The LVIS-92i dataset contains 92 images with 92 object categories.

The PACO-Part dataset contains 59 images with 59 object categories.

The PerSeg dataset contains 40 images with 40 object categories.

COCO validation dataset

Few-shot segmentation aims to segment novel classes by using the model trained on base classes.