MétaCan
Menu
Back to cohort
Record W3132284397

Achieving Explainability in a Visual Hard Attention Model through Content Prediction

2021· article· en· W3132284397 on OpenAlexaff
Samrudhdhi B. Rangrej, James J. Clark

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicVisual Attention and Saliency Detection
Canadian institutionsMcGill University
Fundersnot available
KeywordsComputer scienceImage (mathematics)Artificial intelligenceSequence (biology)Parametric statisticsParametric modelBaseline (sea)Convolution (computer science)Machine learningPattern recognition (psychology)Artificial neural networkStatisticsMathematicsLaw
DOInot available

Abstract

fetched live from OpenAlex

A visual hard attention model actively selects and observes a sequence of subregions in an image to make a prediction. Unlike in the deep convolution network, in hard attention it is explainable which regions of the image contributed to the prediction. However, the attention policy used by the model to select these regions is not explainable. The majority of hard attention models determine the attention-worthy regions by first analyzing a complete image. However, it may be the case that the entire image is not available in the beginning but instead sensed gradually through a series of partial observations. In this paper, we design an efficient hard attention model for classifying partially observable scenes. The attention policy used by our model is explainable and non-parametric. The model estimates expected information gain (EIG) obtained from attending various regions by predicting their content ahead of time. It compares EIG using Bayesian Optimal Experiment Design and attends to the region with maximum EIG. We train our model with a differentiable objective, optimized using gradient descent, and test it on several datasets. The performance of our model is comparable to or better than the baseline models.

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)0.000
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: Empirical · Consensus signal: none
Teacher disagreement score0.777
Threshold uncertainty score0.436

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 studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
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 head0.076
GPT teacher head0.305
Teacher spread0.229 · 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 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

Citations0
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicVisual Attention and Saliency DetectionFrench-language works237,207