The authors expand LeCun's cake metaphor to the full AI lifecycle and argue that social outcomes are constrained by technical foundations such as the i.i.d. assumption, homogenization, catastrophic forgetting, and surrogate objectives.
A study of deep perceptual metrics for image quality assessment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Several metrics exist to quantify the similarity between images, but they are inefficient when it comes to measure the similarity of highly distorted images. In this work, we propose to empirically investigate perceptual metrics based on deep neural networks for tackling the Image Quality Assessment (IQA) task. We study deep perceptual metrics according to different hyperparameters like the network's architecture or training procedure. Finally, we propose our multi-resolution perceptual metric (MR-Perceptual), that allows us to aggregate perceptual information at different resolutions and outperforms standard perceptual metrics on IQA tasks with varying image deformations. Our code is available at https://github.com/ENSTA-U2IS/MR_perceptual
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
ACCEPT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation
The authors expand LeCun's cake metaphor to the full AI lifecycle and argue that social outcomes are constrained by technical foundations such as the i.i.d. assumption, homogenization, catastrophic forgetting, and surrogate objectives.