MétaCan
Menu
Back to cohort
Record W4300649690 · doi:10.48550/arxiv.1803.05082

Revisiting Salient Object Detection: Simultaneous Detection, Ranking,\n and Subitizing of Multiple Salient Objects

2018· preprint· W4300649690 on OpenAlexaff
Md Amirul Islam, Mahmoud Kalash, Neil D. B. Bruce

Bibliographic record

VenuearXiv (Cornell University) · 2018
Typepreprint
Language
FieldComputer Science
TopicVisual Attention and Saliency Detection
Canadian institutionsUniversity of Manitoba
Fundersnot available
KeywordsSalientRepresentation (politics)Computer scienceObject (grammar)Artificial intelligenceRank (graph theory)Ranking (information retrieval)Object detectionMachine learningPattern recognition (psychology)Mathematics

Abstract

fetched live from OpenAlex

Salient object detection is a problem that has been considered in detail and\nmany solutions proposed. In this paper, we argue that work to date has\naddressed a problem that is relatively ill-posed. Specifically, there is not\nuniversal agreement about what constitutes a salient object when multiple\nobservers are queried. This implies that some objects are more likely to be\njudged salient than others, and implies a relative rank exists on salient\nobjects. The solution presented in this paper solves this more general problem\nthat considers relative rank, and we propose data and metrics suitable to\nmeasuring success in a relative object saliency landscape. A novel deep\nlearning solution is proposed based on a hierarchical representation of\nrelative saliency and stage-wise refinement. We also show that the problem of\nsalient object subitizing can be addressed with the same network, and our\napproach exceeds performance of any prior work across all metrics considered\n(both traditional and newly proposed).\n

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)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.439
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.002
Science and technology studies0.0020.001
Scholarly communication0.0000.001
Open science0.0010.002
Research integrity0.0010.001
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 head0.046
GPT teacher head0.204
Teacher spread0.158 · 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
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

Citations1
Published2018
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicVisual Attention and Saliency DetectionFrench-language works237,207