arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1405.0312cs.CV
收藏

Microsoft COCO:上下文中的公共对象

Microsoft COCO: Common Objects in Context

Cornell NYC Tech(康奈尔大学纽约理工校区);Cornell Computer Science Department(康奈尔大学计算机科学系);Toyota Technological Institute at Chicago(芝加哥丰田理工学院);Facebook AI Research(Facebook人工智能研究院);Microsoft Research(微软研究院);Brown University(布朗大学);California Institute of Technology(加州理工学院);University of California at Irvine(加州大学欧文分校)

Tsung-Yi Lin, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, Piotr Dollár

摘要:

我们提出了一个新的数据集,其目标是通过将对象识别问题置于更广泛的场景理解问题的背景下来推进对象识别的最新技术。这是通过收集复杂的日常场景的图像来实现的,这些场景包含自然背景中的常见对象。使用每实例分割来标记对象,以帮助精确的对象定位。我们的数据集包含91个物体类型的照片,这些物体类型很容易被4岁的孩子识别。在328k图像中共有250万个标记实例,我们的数据集的创建通过新颖的用户界面进行类别检测,实例定位和实例分割,利用了广泛的人群工作人员参与。我们对数据集进行了详细的统计分析,并与PASCAL,ImageNet和SUN进行了比较。最后,我们提供基线性能分析的限界框和分割检测结果使用可变形零件模型。

英文摘要:

We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑