MétaCan
Menu
Back to cohort
Record W6950434628 · doi:10.5281/zenodo.8337068

Dynamically Instance-Guided Adaptation: A Backward-free Approach for Test-Time Domain Adaptive Semantic Segmentation

2023· article· en· W6950434628 on OpenAlexaff

Bibliographic record

VenueZenodo (CERN European Organization for Nuclear Research) · 2023
Typearticle
Languageen
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsWestern University
FundersHorizon 2020 Framework Programme
KeywordsSegmentationClassifier (UML)Domain adaptationAdaptation (eye)Parametric statisticsSemantics (computer science)

Abstract

fetched live from OpenAlex

In this paper, we study the application of Test-time<br> domain adaptation in semantic segmentation (TTDA-Seg)<br> where both efficiency and effectiveness are crucial. Existing<br> methods either have low efficiency (e.g., backward optimization)<br> or ignore semantic adaptation (e.g., distribution<br> alignment). Besides, they would suffer from the accumulated<br> errors caused by unstable optimization and abnormal<br> distributions. To solve these problems, we propose a novel<br> backward-free approach for TTDA-Seg, called Dynamically<br> Instance-Guided Adaptation (DIGA). Our principle is utilizing<br> each instance to dynamically guide its own adaptation<br> in a non-parametric way, which avoids the error accumulation<br> issue and expensive optimizing cost. Specifically,<br> DIGA is composed of a distribution adaptation module<br> (DAM) and a semantic adaptation module (SAM), enabling<br> us to jointly adapt the model in two indispensable<br> aspects. DAM mixes the instance and source BN statistics to encourage the model to capture robust representation. SAM<br> combines the historical prototypes with instance-level prototypes<br> to adjust semantic predictions, which can be associated<br> with the parametric classifier to mutually benefit the<br> final results. Extensive experiments evaluated on five target<br> domains demonstrate the effectiveness and efficiency of the<br> proposed method. Our DIGA establishes new state-of-theart<br> performance in TTDA-Seg. Source code is available at:<br> https://github.com/Waybaba/DIGA.

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)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScience and technology studies, Scholarly communication, Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.732
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0020.000
Scholarly communication0.0010.001
Open science0.0020.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.004

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 head0.051
GPT teacher head0.253
Teacher spread0.203 · 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.

Study designSimulation or modeling
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

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueZenodo (CERN European Organization for Nuclear Research)Same topicDomain Adaptation and Few-Shot LearningFrench-language works237,207