MétaCan
Menu
Back to cohort
Record W4301427922 · doi:10.48550/arxiv.1502.07058

Evaluation of Deep Convolutional Nets for Document Image Classification\n and Retrieval

2015· preprint· en· W4301427922 on OpenAlexaff
Adam W. Harley, Alex Ufkes, Konstantinos G. Derpanis

Bibliographic record

VenuearXiv (Cornell University) · 2015
Typepreprint
Languageen
FieldComputer Science
TopicHandwritten Text Recognition Techniques
Canadian institutionsToronto Metropolitan University
Fundersnot available
KeywordsConvolutional neural networkComputer scienceArtificial intelligenceAbstractionPattern recognition (psychology)Representation (politics)Feature (linguistics)Variety (cybernetics)Document classificationObject (grammar)Deep learningFeature learningContextual image classificationImage (mathematics)Information retrieval

Abstract

fetched live from OpenAlex

This paper presents a new state-of-the-art for document image classification\nand retrieval, using features learned by deep convolutional neural networks\n(CNNs). In object and scene analysis, deep neural nets are capable of learning\na hierarchical chain of abstraction from pixel inputs to concise and\ndescriptive representations. The current work explores this capacity in the\nrealm of document analysis, and confirms that this representation strategy is\nsuperior to a variety of popular hand-crafted alternatives. Experiments also\nshow that (i) features extracted from CNNs are robust to compression, (ii) CNNs\ntrained on non-document images transfer well to document analysis tasks, and\n(iii) enforcing region-specific feature-learning is unnecessary given\nsufficient training data. This work also makes available a new labelled subset\nof the IIT-CDIP collection, containing 400,000 document images across 16\ncategories, useful for training new CNNs for document analysis.\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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.905
Threshold uncertainty score0.874

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
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 science0.0010.001
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 head0.142
GPT teacher head0.259
Teacher spread0.116 · 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 designTheoretical or conceptual
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

Citations3
Published2015
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicHandwritten Text Recognition TechniquesFrench-language works237,207