MétaCan
Menu
Back to cohort

Search, Estimate, and Predict: Efficient Weakly-Supervised Learning

2024· article· en· W4404565353 on OpenAlexaff
Bokuan Yang, Jinghai Cao, Jessie M. Wu, Yuanqi Wu, Jie Zhang, Changyong Pan

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicFace and Expression Recognition
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsComputer scienceMachine learningArtificial intelligenceSupervised learningArtificial neural network

Abstract

fetched live from OpenAlex

Most of state-of-the-arts region-based detectors are suffered from the requirement of training for a large volume of bounding box annotated data. In this paper, we propose an innovative weakly-supervised architecture, namely SEP-Net, that employs an efficient proposal searching method on feature maps to generate region proposals via transforming CNN classifiers to object detectors without bounding box annotations. We further show the proposed framework can be used for real-time detection, in which high computation efficiency is a prerequisite. Moreover, the training procedure is exactly the same as what’s for CNN classifiers, so is easy to transfer a pre-trained CNN to our weakly-supervised detector as well. Experimental validation on ImageNet 2012 dataset show that the novel model outperforms classical and most recent state-of-the-art weakly-supervised method by a wide margin in terms of both accuracy and efficiency.

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 score0.972
Threshold uncertainty score0.401

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 communication0.0000.000
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 head0.014
GPT teacher head0.259
Teacher spread0.246 · 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
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicFace and Expression RecognitionFrench-language works237,207