在本文中,我们研究了针对泊松方程的解决方案的概率和神经网络近似,但在$ \ mathbb {r}^d $的一般边界域中,较旧或$ c^2 $数据。我们的目标是两个基本目标。首先,也是最重要的是,我们证明了泊松方程的解决方案可以通过蒙特卡洛方法在sup-norm中进行数值近似,但基于球形算法的步行略有变化。这提供了相对于相对于相对于相对于有效的估计值规定的近似误差且没有维度的诅咒。此外,样品的总数不取决于执行近似的点。作为第二个目标,我们表明获得的蒙特卡洛求解器renders relu relu深层神经网络(DNN)解决泊松问题的解决方案,其大小在尺寸$ d $以及所需的错误中大多数取决于多项式。和低多项式复杂性。
translated by 谷歌翻译
自动对象检测器的本地化质量通常通过联合(IOU)分数进行评估。在这项工作中,我们表明人类对本地化质量有不同的看法。为了评估这一点,我们对70多名参与者进行了调查。结果表明,对于以完全相同的评分而言,人类可能不会认为这些错误是相等的,并且表达了偏好。我们的工作是第一个与人类一起评估IOU的工作,并清楚地表明,仅依靠IOU分数来评估本地化错误可能还不够。
translated by 谷歌翻译
We propose a method that can generate an unambiguous description (known as a referring expression) of a specific object or region in an image, and which can also comprehend or interpret such an expression to infer which object is being described. We show that our method outperforms previous methods that generate descriptions of objects without taking into account other potentially ambiguous objects in the scene. Our model is inspired by recent successes of deep learning methods for image captioning, but while image captioning is difficult to evaluate, our task allows for easy objective evaluation. We also present a new large-scale dataset for referring expressions, based on MS-COCO. We have released the dataset and a toolbox for visualization and evaluation, see https://github.com/ mjhucla/Google_Refexp_toolbox.
translated by 谷歌翻译