MétaCan
Menu
Back to cohort
Record W4308085167 · doi:10.1109/cases55004.2022.00024

Work-in-Progress: SuperNAS: Fast Multi-Objective SuperNet Architecture Search for Semantic Segmentation

2022· article· en· W4308085167 on OpenAlexaff
Marihan Amein, Zhuoran Xiong, Olivier Therrien, Brett H. Meyer, Warren J. Gross

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Neural Network Applications
Canadian institutionsMcGill University
Fundersnot available
KeywordsComputer sciencePascal (unit)SegmentationFLOPSPareto principleTraining setPareto optimalMachine learningArtificial intelligenceArchitectureSet (abstract data type)Multi-objective optimizationData miningPattern recognition (psychology)Parallel computingMathematical optimizationMathematics

Abstract

fetched live from OpenAlex

We present SuperNAS, a fast multi-objective neural architecture search framework for semantic segmentation. SuperNAS subsamples the structure and pre-trained parameters of DeepLabV3+, without fine-tuning, dramatically reducing training time during search. To further reduce candidate evaluation time, we use a subset of the validation dataset during search. Only the final, Pareto-dominant, candidates are ultimately fine-tuned using the complete training set. We evaluate SuperNAS by searching for models that effectively trade accuracy and computational cost on the PASCAL VOC 2012 dataset. SuperNAS finds competitive designs quickly, e.g., taking just 0.5 GPU days to discover a DeepLabV3+ variant that reduces FLOPs and parameters by 10% and 20% respectively, for less than 3% increased error.

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)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.021
Threshold uncertainty score0.070

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0030.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0020.003
Open science0.0040.002
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0210.006

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 head0.025
GPT teacher head0.299
Teacher spread0.273 · 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 designBench or experimental
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

Citations2
Published2022
Admission routes1
Has abstractyes

Explore more

Same topicAdvanced Neural Network ApplicationsFrench-language works237,207