MétaCan
Menu
Back to cohort
Record W4293868331 · doi:10.1109/crv55824.2022.00015

Semi-supervised Grounding Alignment for Multi-modal Feature Learning

2022· article· en· W4293868331 on OpenAlex

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.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicMultimodal Machine Learning Applications
Canadian institutionsVector InstituteCanadian Institute for Advanced ResearchUniversity of British Columbia
Fundersnot available
KeywordsComputer scienceArtificial intelligencePhraseMargin (machine learning)Leverage (statistics)Machine learningGroundSentenceFeature (linguistics)TransformerModalClassifier (UML)Feature learningNatural language processingQuestion answeringSupervised learningFeature extractionPattern recognition (psychology)Artificial neural networkEngineering

Abstract

fetched live from OpenAlex

Self-supervised transformer-based architectures, such as ViLBERT [1] and others, have recently emerged as dominant paradigms for multi-modal feature learning. Such architectures leverage large-scale datasets (e.g., Conceptual Captions [2]) and, typically, image-sentence pairings, for self-supervision. However, conventional multi-modal feature learning requires huge datasets and computing for both pre-training and fine-tuning to the target task. In this paper, we illustrate that more granular semi-supervised alignment at a region-phrase level is an additional useful cue and can further improve the performance of such representations. To this end, we propose a novel semi-supervised grounding alignment loss, which leverages an off-the-shelf pre-trained phrase grounding model for pseudo-supervision (by producing region-phrase alignments). This semi-supervised formulation enables better feature learning in the absence of any additional human annotations on the large-scale (Conceptual Captions) dataset. Further, it shows an even larger margin of improvement on smaller data splits, leading to effective data-efficient feature learning. We illustrate the superiority of the learned features by fine-tuning the resulting models to multiple vision-language downstream tasks: visual question answering (VQA), visual commonsense reasoning (VCR), and visual grounding. Experiments on the VQA, VCR, and grounding benchmarks demonstrate the improvement of up to 1.3&#x0025; in accuracy (in visual grounding) with large-scale training; up to 5.9&#x0025; (in VQA) with 1/8 of the data for pre-training and fine-tuning<sup>1</sup><sup>1</sup>We will release the code and all pre-trained models upon acceptance..

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)0.000
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: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.713
Threshold uncertainty score0.878

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0010.001
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 head0.032
GPT teacher head0.302
Teacher spread0.271 · 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

Quick stats

Citations5
Published2022
Admission routes1
Has abstractyes

Explore more

Same topicMultimodal Machine Learning ApplicationsFrench-language works237,207