arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2004.11498cs.CV
收藏

挖掘自相似性:基于表位表示的标签超分辨率

Mining self-similarity: Label super-resolution with epitomic representations

Yale University(耶鲁大学);Microsoft AI for Good Research Lab(微软人工智能公益研究实验室);Microsoft Research(微软研究院)

Nikolay Malkin, Anthony Ortiz, Caleb Robinson, Nebojsa Jojic

摘要:

我们表明,简单的基于补丁的模型,如摘要,可以有更优越的性能,目前的最先进的语义分割和标签超分辨率,它使用深卷积神经网络。我们推导出一种新的训练算法的表位,它允许,第一次,从非常大的数据集学习,并得出标签超分辨率算法作为一个统计推断算法的表位表示。我们说明了我们的土地覆盖制图和医学图像分析任务的方法。

英文摘要:

We show that simple patch-based models, such as epitomes, can have superior performance to the current state of the art in semantic segmentation and label super-resolution, which uses deep convolutional neural networks. We derive a new training algorithm for epitomes which allows, for the first time, learning from very large data sets and derive a label super-resolution algorithm as a statistical inference algorithm over epitomic representations. We illustrate our methods on land cover mapping and medical image analysis tasks.

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。

↑