MétaCan
Menu
Back to cohort

Double Encoding - Slow Decoding Image to Image CNN for Foreground Identification with Application Towards Intelligent Transportation

2018· article· en· W2948538458 on OpenAlexaff
Thangarajah Akilan, Q. M. Jonathan Wu

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicVisual Attention and Saliency Detection
Canadian institutionsUniversity of Windsor
Fundersnot available
KeywordsComputer scienceDecoding methodsArtificial intelligenceConvolutional neural networkEncoderEncoding (memory)Pattern recognition (psychology)Feature (linguistics)Computer visionSegmentationImage segmentationAlgorithm

Abstract

fetched live from OpenAlex

The vision-based foreground (FG) identification approaches are in great demand to intelligent transportation applications. Here, the convolutional neural network (CNN)-based image-to-image models have shown impressive performance in saliency detection and semantic segmentation. Inspired by their advancement in computer vision (CV), we introduce a strategy, named double encoding - slow decoding to improve a basic encoder-decoder (EnDec) CNN for precise FG masking. Wherein, at every stage of down-sampling, a feature map is encoded twice and every stage of up-sampling is enhanced by two residual feature concatenations (cat) and interspersed batch normalization (BN). Such continuous forward feature pulling process in the encoding and decoding sub-networks results delineated FG identification. We carry out a thorough analysis to validate the effectiveness of the proposed model in terms of figure of merit (f-measure). We also investigate four different methods of FG binary mask creation from the probability saliency map generated by the model. The experimental study on benchmark datasets proves that the proposed architecture achieves better/competitive results than/against state-of-the-art methods.

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)0.000
metaresearch head score (Gemma)0.001
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: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.007
Threshold uncertainty score0.013

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.001

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 head0.031
GPT teacher head0.322
Teacher spread0.291 · 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

Citations5
Published2018
Admission routes1
Has abstractyes

Explore more

Same topicVisual Attention and Saliency DetectionFrench-language works237,207