A Powerful Generative Model Using Random Weights for the Deep Image Representation
This work provides a new tool for studying deep network representations, suggesting that architecture alone may suffice for visualization, which could impact researchers in computer vision and neural network interpretability.
The authors demonstrated that untrained, random-weight convolutional neural networks can perform three deep visualization tasks—image reconstruction, texture synthesis, and style transfer—with results statistically superior or competitive to those using trained networks, achieving high perceptual quality and indistinguishable textures.
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.