29 datasets found

The CityPersons dataset is a new pedestrian detection dataset, consisting of 500 images with annotated objects.

The Caltech dataset is a large-scale dataset for pedestrian detection, consisting of 4024 images with annotated objects.

The KITTI dataset is a large-scale dataset for autonomous driving, consisting of 15,000 images with annotated objects.

The SUNRGB-D dataset features 5,285 training and 5,050 test samples from multiple RGB-D cameras. The dataset provides annotations for the first 37 NYUv2 semantic classes and for...

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 dataset used in the paper is a synthetic dataset for image-based object detection tasks, specifically instance segmentation and monocular 3D detection.

The dataset used in the paper is the COCO object detection and instance segmentation dataset, and the ADE20K semantic segmentation dataset.

The VOC2012 dataset is a multi-label image recognition dataset. It contains 11,540 train-val images and 10,991 test 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...

The dataset used in the paper is ImageNet-1K, ADE20K, and COCO 2017.

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

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,...

Scene segmentation in images is a fundamental yet challenging problem in visual content understanding, which is to learn a model to assign every image pixel to a categorical label.

The Cityscapes dataset consists of 8 thing classes and 11 stuff classes.

The dataset used in the paper is ImageNet, MS COCO, and Pascal VOC datasets.

Multi-task learning (MTL) research is broadly divided into two categories: one is to learn the correlation between tasks through model structures, and the other is to balance...

A point cloud dataset with large quantity of dynamic instances, consisting of 2,988 real-world scans with point-level annotations.

Semantic segmentation is a crucial and challenging task for image understanding. It aims to predict a dense labeling map for the input image, which assigns each pixel a unique...