arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.06155cs.LGcs.CVstat.ML
收藏

深度广义卷积和积网络

Deep Generalized Convolutional Sum-Product Networks

KTH Royal Institute of Technology(瑞典皇家理工学院);MessageBird(MessageBird公司);University of Washington(华盛顿大学)

Jos van de Wolfshaar, Andrzej Pronobis

摘要:

和积网络(SPN)是一种分层的图形模型,结合了深度学习和概率建模的优点。SPN为需要对高维噪声输入进行精确概率推理的应用提供了独特的优势。然而,与卷积神经网络相比,它们难以捕捉图像数据中复杂的空间关系。为了缓解这个问题,我们引入了深度广义卷积和积网络(DGC-SPN),它以类似于CNN的方式对空间特征进行编码,同时保留了概率SPN模型的有效性。与现有的基于SPN的图像表示相反,DGC-SPN允许通过膨胀和步幅的新参数化来重叠卷积补丁,从而显著提高特征覆盖率和特征分辨率。DGC-SPN在多个视觉数据集上以及在生成和区分任务(包括图像修补和分类)上都大大优于其他SPN架构。这些贡献通过第一个简单,可扩展和GPU优化的SPN实现得到了加强,并与广泛使用的Keras/TensorFlow框架集成。由此产生的模型是完全概率和通用的,但有效和直接应用于实际应用中,代替传统的深度网络。

英文摘要:

Sum-Product Networks (SPNs) are hierarchical, graphical models that combine benefits of deep learning and probabilistic modeling. SPNs offer unique advantages to applications demanding exact probabilistic inference over high-dimensional, noisy inputs. Yet, compared to convolutional neural nets, they struggle with capturing complex spatial relationships in image data. To alleviate this issue, we introduce Deep Generalized Convolutional Sum-Product Networks (DGC-SPNs), which encode spatial features in a way similar to CNNs, while preserving the validity of the probabilistic SPN model. As opposed to existing SPN-based image representations, DGC-SPNs allow for overlapping convolution patches through a novel parameterization of dilations and strides, resulting in significantly improved feature coverage and feature resolution. DGC-SPNs substantially outperform other SPN architectures across several visual datasets and for both generative and discriminative tasks, including image inpainting and classification. These contributions are reinforced by the first simple, scalable, and GPU-optimized implementation of SPNs, integrated with the widely used Keras/TensorFlow framework. The resulting model is fully probabilistic and versatile, yet efficient and straightforward to apply in practical applications in place of traditional deep nets.

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。

↑