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 1606.04801cs.CVcs.LGcs.NE
收藏

一种用于深度图像表示的强大的随机权重生成模型

A Powerful Generative Model Using Random Weights for the Deep Image Representation

Huazhong University of Science and Technology(华中科技大学);Cornell University(康奈尔大学)

Kun He, Yan Wang, John Hopcroft

摘要:

深度可视化的成功在多大程度上是由于训练?我们可以使用未经训练的随机权重网络进行深度可视化吗?为了解决这个问题,我们使用未经训练的随机权重卷积神经网络为三个流行的深度可视化任务探索新的强大的生成模型。首先,我们反转特征空间中的表示,并从白噪声输入中重建图像。重建质量在统计上高于应用于具有相同架构的良好训练的网络的相同方法。接下来,我们使用多层表示的缩放相关性来合成纹理,我们的结果与原始自然纹理和基于训练网络的合成纹理几乎无法区分。第三,通过以各种艺术作品的风格重铸图像的内容,我们创建了具有高感知质量的艺术图像,与Gatys等人在预训练网络上的先前工作具有高度竞争力。据我们所知,这是第一次使用未经训练的深度神经网络进行图像表示。我们的工作提供了一个新的和迷人的工具来研究深度网络架构的表示,并揭示了对深度可视化的新理解。

英文摘要:

To what extent is the success of deep visualization due to the training? Could we do deep visualization using untrained, random weight networks? To address this issue, we explore new and powerful generative models for three popular deep visualization tasks using untrained, random weight convolutional neural networks. First we invert representations in feature spaces and reconstruct images from white noise inputs. The reconstruction quality is statistically higher than that of the same method applied on well trained networks with the same architecture. Next we synthesize textures using scaled correlations of representations in multiple layers and our results are almost indistinguishable with the original natural texture and the synthesized textures based on the trained network. Third, by recasting the content of an image in the style of various artworks, we create artistic images with high perceptual quality, highly competitive to the prior work of Gatys et al. on pretrained networks. To our knowledge this is the first demonstration of image representations using untrained deep neural networks. Our work provides a new and fascinating tool to study the representation of deep network architecture and sheds light on new understandings on deep visualization.

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。

↑