论文标题
深度模板网络的印象空间
Impression Space from Deep Template Network
论文作者
论文摘要
人类只有根据他们的印象来想象某些东西,而不必记住他们所看到的所有细节,这是一种天生的能力。在这项工作中,我们要证明训练有素的卷积神经网络还具有“记住”其输入图像的能力。为了实现这一目标,我们提出了一个简单但功能强大的框架,以在现成的预处理网络上建立{\ emph {Impression Space}}。该网络被称为{\ emph {Template Network}},因为其过滤器将用作从印象中重建图像的模板。在我们的框架中,印象空间和图像空间是通过层面编码和迭代解码过程桥接的。事实证明,印象空间确实捕获了图像中的显着特征,并且可以直接应用于诸如未配对的图像翻译和图像合成之类的任务,而无需进一步的网络训练。此外,印象自然会为不同数据构建高级共同空间。基于此,我们提出了一种机制来对印象空间内的数据关系进行建模,该机制能够揭示图像之间的特征相似性。我们的代码将发布。
It is an innate ability for humans to imagine something only according to their impression, without having to memorize all the details of what they have seen. In this work, we would like to demonstrate that a trained convolutional neural network also has the capability to "remember" its input images. To achieve this, we propose a simple but powerful framework to establish an {\emph{Impression Space}} upon an off-the-shelf pretrained network. This network is referred to as the {\emph{Template Network}} because its filters will be used as templates to reconstruct images from the impression. In our framework, the impression space and image space are bridged by a layer-wise encoding and iterative decoding process. It turns out that the impression space indeed captures the salient features from images, and it can be directly applied to tasks such as unpaired image translation and image synthesis through impression matching without further network training. Furthermore, the impression naturally constructs a high-level common space for different data. Based on this, we propose a mechanism to model the data relations inside the impression space, which is able to reveal the feature similarity between images. Our code will be released.