首页
学习
活动
专区
工具
TVP
发布
精选内容/技术社群/优惠产品,尽在小程序
立即前往
  • 您找到你想要的搜索结果了吗?
    是的
    没有找到

    unsupervised learning layers for label-free video analysis

    This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones. The proposed UL layers can play two roles: they can be the cost function layer for providing global training signal; meanwhile they can be added to any regular neural network layers for providing local training signals and combined with the training signals backpropagated from upper layers for extracting both slow and fast changing features at layers of different depths. Therefore, the UL layers can be used in either pure unsupervised or semi-supervised settings. Both a closed-form solution and an online learning algorithm for two UL layers are provided. Experiments with unlabeled synthetic and real-world videos demonstrated that the neural networks equipped with UL layers and trained with the proposed online learning algorithm can extract shape and motion information from video sequences of moving objects. The experiments demonstrated the potential applications of UL layers and online learning algorithm to head orientation estimation and moving object localization.

    03

    科学出版物视觉总结识别的自我监督学习(CS)

    提供科学出版物的可视化摘要可以增加读者获得信息的机会,从而有助于应对科学出版物数量的指数级增长。然而,很少有提供视觉出版物摘要, 而且主要侧重于生物医学领域。这主要是因为有注释的黄金标准有限,这妨碍了可靠和高绩效监督学习技术的应用。为了解决这些问题 ,我们创建一个新的基准数据集,用于选择数字,以根据出版物摘要作为出版物的可视化摘要,涵盖计算机科学的几个领域。此外,我们开发一种自我监督的学习方法,基于对数字与数字标题的内联引用的启发式匹配。生物医学和计算机科学领域的实验表明,尽管我们自我监督,并因此不依赖任何带注释的培训数据,但我们的模型能够超越最先进的技术。

    00

    DEEP PROBABILISTIC PROGRAMMING 深度概率编程

    We propose Edward, a Turing-complete probabilistic programming language. Edward builds on two compositional representations---random variables and inference. By treating inference as a first class citizen, on a par with modeling, we show that probabilistic programming can be as flexible and computationally efficient as traditional deep learning. For flexibility, Edward makes it easy to fit the same model using a variety of composable inference methods, ranging from point estimation, to variational inference, to MCMC. In addition, Edward can reuse the modeling representation as part of inference, facilitating the design of rich variational models and generative adversarial networks. For efficiency, Edward is integrated into TensorFlow, providing significant speedups over existing probabilistic systems. For example, on a benchmark logistic regression task, Edward is at least 35x faster than Stan and PyMC3.

    03
    领券