MétaCan
Menu
Back to cohort
Record W4400314741 · doi:10.1109/jsait.2024.3422011

JPEG Compliant Compression for DNN Vision

2024· article· en· W4400314741 on OpenAlex
Ahmed H. Salamah, Kaixiang Zheng, Linfeng Ye, En‐hui Yang

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueIEEE Journal on Selected Areas in Information Theory · 2024
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Data Compression Techniques
Canadian institutionsUniversity of Waterloo
FundersNatural Sciences and Engineering Research Council of CanadaCanada Research Chairs
KeywordsComputer scienceJPEGCompression (physics)Computer visionJPEG 2000Artificial intelligenceImage compressionData compressionImage processingMaterials scienceImage (mathematics)Composite material

Abstract

fetched live from OpenAlex

Conventional image compression techniques are primarily developed for the human visual system. However, with the extensive use of deep neural networks (DNNs) for computer vision, more and more images will be consumed by DNN-based intelligent machines, which makes it crucial to develop image compression techniques customized for DNN vision while being JPEG compliant. In this paper, we revisit the JPEG rate distortion theory for DNN vision. First, we propose a novel distortion measure, dubbed the sensitivity weighted error (SWE), for DNN vision. Second, we incorporate SWE into the soft decision quantization (SDQ) process of JPEG to trade SWE for rate. Finally, we develop an algorithm, called OptS, for designing optimal quantization tables for the luminance channel and chrominance channels, respectively. To test the performance of the resulting DNN-oriented compression framework and algorithm, experiments of image classification are conducted on the ImageNet dataset for four prevalent DNN models. Results demonstrate that our proposed framework and algorithm achieve better rate-accuracy (R-A) performance than the default JPEG. For some DNN models, our proposed framework and algorithm provide a significant reduction in the compression rate up to 67.84% with no accuracy loss compared to the default JPEG.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.844
Threshold uncertainty score0.679

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.005
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.013
GPT teacher head0.305
Teacher spread0.292 · 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