MétaCan
Menu
Back to cohort
Record W4407176389 · doi:10.2352/cic.2024.32.1.10

Neural Image Compression and the Degradation of Color: An Analysis

2024· article· en· W4407176389 on OpenAlexfundno aff
Ian MacPherson, Trevor Canham, Michael S. Brown

Bibliographic record

VenueColor and Imaging Conference · 2024
Typearticle
Languageen
FieldComputer Science
TopicImage and Signal Denoising Methods
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of CanadaCanada First Research Excellence Fund
KeywordsDegradation (telecommunications)Artificial intelligenceCompression (physics)Image (mathematics)Computer visionComputer sciencePattern recognition (psychology)Materials scienceComposite material

Abstract

fetched live from OpenAlex

Neural image compression employs deep neural networks and generative models to achieve impressive compression rates and reconstruction qualities compared to traditional signal-processing-based compression algorithms such as JPEG. However, color artifacts that arise in an image as the amount of compression increases have not been formally analyzed for neural-based compression algorithms. This paper provides an initial investigation into the degradation of color when images are compressed at comparable bit rates using lossy neural image compression and variants of JPEG. Our findings indicate that neural image compression degrades color more gracefully than JPEG, JPEG 2000, and JPEG XL.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.002
Threshold uncertainty score0.005

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.001
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.021
GPT teacher head0.302
Teacher spread0.281 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueColor and Imaging ConferenceSame topicImage and Signal Denoising MethodsFrench-language works237,207