MétaCan
Menu
Back to cohort
Record W4385834335 · doi:10.1109/access.2023.3305576

UnShadowNet: Illumination Critic Guided Contrastive Learning for Shadow Removal

2023· article· en· W4385834335 on OpenAlexaff
Subhrajyoti Dasgupta, Arindam Das, Senthil Yogamani, Sudip Das, Ciarán Eising, Andrei Bursuc, Ujjwal Bhattacharya

Bibliographic record

VenueIEEE Access · 2023
Typearticle
Languageen
FieldComputer Science
TopicImage Enhancement Techniques
Canadian institutionsMila - Quebec Artificial Intelligence Institute
Fundersnot available
KeywordsComputer scienceArtificial intelligenceShadow (psychology)

Abstract

fetched live from OpenAlex

Shadows are frequently encountered natural phenomena that significantly hinder the performance of computer vision perception systems in practical settings, e.g., autonomous driving. A solution to this would be to eliminate shadow regions from the images before the processing of the perception system. Yet, training such a solution requires pairs of aligned shadowed and non-shadowed images which are difficult to obtain. We introduce a novel weakly supervised shadow removal framework <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">UnShadowNet</i> trained using contrastive learning. It is composed of a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DeShadower</i> network responsible for the removal of the extracted shadow under the guidance of an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Illumination</i> network which is trained adversarially by the illumination critic and a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Refinement</i> network to further remove artefacts. We show that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">UnShadowNet</i> can be easily extended to a fully-supervised set-up to exploit the ground-truth when available. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">UnShadowNet</i> outperforms existing state-of-the-art approaches on three publicly available shadow datasets (ISTD, adjusted ISTD, SRD) in both the weakly and fully supervised setups.

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 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: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.959
Threshold uncertainty score0.571

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
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 head0.056
GPT teacher head0.361
Teacher spread0.305 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreMethods

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

Citations8
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueIEEE AccessSame topicImage Enhancement TechniquesFrench-language works237,207