Inverting Adversarially Robust Networks for Image Synthesis
release_od4hcydjzfhltb3hnvuwfjuvwm
by
Renan A. Rojas-Gomez, Raymond A. Yeh, Minh N. Do, Anh Nguyen
2021
Abstract
Recent research in adversarially robust classifiers suggests their
representations tend to be aligned with human perception, which makes them
attractive for image synthesis and restoration applications. Despite favorable
empirical results on a few downstream tasks, their advantages are limited to
slow and sensitive optimization-based techniques. Moreover, their use on
generative models remains unexplored. This work proposes the use of robust
representations as a perceptual primitive for feature inversion models, and
show its benefits with respect to standard non-robust image features. We
empirically show that adopting robust representations as an image prior
significantly improves the reconstruction accuracy of CNN-based feature
inversion models. Furthermore, it allows reconstructing images at multiple
scales out-of-the-box. Following these findings, we propose an
encoding-decoding network based on robust representations and show its
advantages for applications such as anomaly detection, style transfer and image
denoising.
In text/plain
format
Archived Content
There are no accessible files associated with this release. You could check other releases for this work for an accessible version.
Know of a fulltext copy of on the public web? Submit a URL and we will archive it
2106.06927v1
access all versions, variants, and formats of this works (eg, pre-prints)