Timezone: »
Features extracted from deep layers of classification networks are widely used as image descriptors. Here, we exploit an unexplored property of these features: their internal dissimilarity. While small image patches are known to have similar statistics across image scales, it turns out that the internal distribution of deep features varies distinctively between scales. We show how this deep self dissimilarity (DSD) property can be used as a powerful visual fingerprint. Particularly, we illustrate that full-reference and no-reference image quality measures derived from DSD are highly correlated with human preference. In addition, incorporating DSD as a loss function in training of image restoration networks, leads to results that are at least as photo-realistic as those obtained by GAN based methods, while not requiring adversarial training.
Author Information
Idan Kligvasser (Technion, Technion)
Tamar Shaham (Technion, Technion)
Yuval Bahat (Technion, Technion)
Tomer Michaeli (Technion, Technion)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Spotlight: Deep Self-Dissimilarities as Powerful Visual Fingerprints »
Dates n/a. Room
More from the Same Authors
-
2021 Poster: Catch-A-Waveform: Learning to Generate Audio from a Single Short Example »
Gal Greshler · Tamar Shaham · Tomer Michaeli -
2021 Poster: The Implicit Bias of Minima Stability: A View from Function Space »
Rotem Mulayoff · Tomer Michaeli · Daniel Soudry -
2021 Poster: A Theory of the Distortion-Perception Tradeoff in Wasserstein Space »
Dror Freirich · Tomer Michaeli · Ron Meir