图像语义分割常用数据库

1.PASCAL VOC2012
http://host.robots.ox.ac.uk/pascal/VOC/voc2012/
20类,包括person
benchmark leaderboard:
http://host.robots.ox.ac.uk:8080/leaderboard/displaylb.php?challengeid=11&compid=6

目前效果最好的来自google的DeepLabv3-JFT 模型。

2.MS COCO
http://cocodataset.org
The COCO train, validation, and test sets, containing more than 200,000 images and 80 object categories, are available on the download page. All object instances are annotated with a detailed segmentation mask. Annotations on the training and validation sets (with over 500,000 object instances segmented) are publicly available.

3.ADE20K
https://groups.csail.mit.edu/vision/datasets/ADE20K/
http://sceneparsing.csail.mit.edu/
20000张训练数据,2000张val数据.若干张test数据(需要上传结果到服务器才能得到结果),150类。场景包括室内室外各种各样的场景.

4.PASCAL Context
数据是基于PASCAL VOC 2010做的标记
http://host.robots.ox.ac.uk/pascal/VOC/voc2010/#data
Training and validation contains 10,103 images while testing contains 9,637 images.

5.PASCAL-Part Dataset
http://www.stat.ucla.edu/~xianjie.chen/pascal_part_dataset/pascal_part.html

6.Cityscapes
https://www.cityscapes-dataset.com/
Cityscapes is a recently released large-scale dataset, which contains high quality pixel-level annotations of 5000 images collected in street scenes from 50 different cities. Following the evaluation protocol [37], 19 semantic labels (belonging to 7 super categories: ground, construc- tion, object, nature, sky, human, and vehicle) are used for evaluation (the void label is not considered for evaluation). The training, validation, and test sets contain 2975, 500, and 1525 images respectively.

7.A2D
https://web.eecs.umich.edu/~jjcorso/r/a2d/index.html
The A2D has 3782 videos with at least 99 instances per valid actor-action tuple and videos are labeled with both pixel-level actors and actions for sampled frames. The A2D dataset serves as a novel large-scale testbed for various vision problems: video-level single- and multiple-label actor-action recognition, instance-level object segmentation/co-segmentation, as well as pixel-level actor-action semantic segmentation to name a few.

8.SYNTHIA
http://synthia-dataset.net
计算机合成的城市道路驾驶环境的像素级标注的数据集。

9.CamVid
http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/

10.Automatic Portrait Segmentation for Image Stylization
http://xiaoyongshen.me/webpage_portrait/index.html
人体肖像分割数据库

转载请注明:《图像语义分割常用数据库

发表评论