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 1709.00069cs.CV
收藏

计算机视觉的学习推理模型

Learning Inference Models for Computer Vision

Eberhard Karls Universität Tübingen(蒂宾根大学)

Varun Jampani

摘要:

计算机视觉可以理解为对图像数据执行推理的能力。计算机视觉技术的突破性进展往往以推理技术的进步为标志。本论文提出了新颖的推理方案,并展示了在计算机视觉中的应用。我们提出了生成和判别视觉模型的推理技术。在视觉中使用生成模型往往受到后验推理困难的阻碍。我们提出了改进MCMC采样和消息传递推理的技术。我们的推理策略是学习独立的判别模型,以辅助贝叶斯推理的生成模型。在一系列生成模型上的实验表明,所提出的技术加速了推理过程和/或收敛到更好的解决方案。判别模型设计中的一个主要复杂性是包含先验知识。我们专注于CNN模型,并提出了一个标准的空间卷积双边卷积的推广。我们概括了现有的双边过滤器的使用,然后提出了新的神经网络架构与可学习的双边过滤器,我们称之为“双边神经网络”。实验证明了双边网络在广泛的图像和视频任务和数据集上的使用。总之,我们提出了更好的推理技术,在几个视觉模型,从逆图形自由参数化神经网络。在生成模型中,我们的推理技术减轻了贝叶斯后验推理中的一些关键障碍,为基于模型的机器学习在视觉中的应用铺平了新的道路。在判别式CNN模型中,所提出的滤波器泛化有助于设计新的神经网络架构,该架构可以处理稀疏的高维数据,并提供一种将先验知识纳入CNN的方法。

英文摘要:

Computer vision can be understood as the ability to perform inference on image data. Breakthroughs in computer vision technology are often marked by advances in inference techniques. This thesis proposes novel inference schemes and demonstrates applications in computer vision. We propose inference techniques for both generative and discriminative vision models. The use of generative models in vision is often hampered by the difficulty of posterior inference. We propose techniques for improving inference in MCMC sampling and message-passing inference. Our inference strategy is to learn separate discriminative models that assist Bayesian inference in a generative model. Experiments on a range of generative models show that the proposed techniques accelerate the inference process and/or converge to better solutions. A main complication in the design of discriminative models is the inclusion of prior knowledge. We concentrate on CNN models and propose a generalization of standard spatial convolutions to bilateral convolutions. We generalize the existing use of bilateral filters and then propose new neural network architectures with learnable bilateral filters, which we call `Bilateral Neural Networks'. Experiments demonstrate the use of the bilateral networks on a wide range of image and video tasks and datasets. In summary, we propose techniques for better inference in several vision models ranging from inverse graphics to freely parameterized neural networks. In generative models, our inference techniques alleviate some of the crucial hurdles in Bayesian posterior inference, paving new ways for the use of model based machine learning in vision. In discriminative CNN models, the proposed filter generalizations aid in the design of new neural network architectures that can handle sparse high-dimensional data as well as provide a way to incorporate prior knowledge into CNNs.

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。

↑