Eigen-Distortions of Hierarchical Representations

Authors: Alexander Berardino, Valero Laparra, Johannes Ballé, Eero Simoncelli

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We develop a method for comparing hierarchical image representations in terms of their ability to explain perceptual sensitivity in humans. ... We use this method to test the ability of a variety of representations to mimic human perceptual sensitivity.
Researcher Affiliation Collaboration Alexander Berardino Center for Neural Science New York University agb313@nyu.edu Johannes Ballé Center for Neural Science New York University johannes.balle@nyu.edu Valero Laparra Image Processing Laboratory Universitat de València valero.laparra@uv.es Eero Simoncelli Howard Hughes Medical Institute, Center for Neural Science and Courant Institute of Mathematical Sciences New York University eero.simoncelli@nyu.edu
Pseudocode No The paper describes the power iteration method verbally with equations, but it does not contain a structured pseudocode or algorithm block labeled as such.
Open Source Code No The paper provides a link to example images and additional examples, but it does not include an unambiguous statement or direct link for the source code of the described methodology.
Open Datasets Yes For each model under consideration, we synthesized extremal eigen-distortions for 6 images from the Kodak image set2. Downloaded from http://www.cipr.rpi.edu/resource/stills/kodak.html. We trained all of the models on the TID-2008 database, which contains a large set of original and distorted images, along with corresponding human ratings of perceived distortion [Ponomarenko et al., 2009].
Dataset Splits No The paper states 'evaluated each model s predictive performance using traditional cross-validation methods on a held-out test set of the TID-2008 database', but it does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology).
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions the use of the Adam algorithm but does not provide specific software details like library names with version numbers needed to replicate the experiment.
Experiment Setup No The paper mentions the use of specific optimization algorithms (non-negative least squares, Adam) but does not provide specific experimental setup details such as concrete hyperparameter values or comprehensive training configurations.