MétaCan
Menu
Back to cohort
Record W2511012736

Visual object recognition using generative models of images

2010· dissertation· en· W2511012736 on OpenAlexaff
Vinod Nair

Bibliographic record

VenueTSpace · 2010
Typedissertation
Languageen
FieldComputer Science
TopicImage Retrieval and Classification Techniques
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsDiscriminative modelArtificial intelligenceGenerative modelComputer sciencePattern recognition (psychology)Generative grammarObject (grammar)Cognitive neuroscience of visual object recognitionSet (abstract data type)Image (mathematics)Machine learning
DOInot available

Abstract

fetched live from OpenAlex

Visual object recognition is one of the key human capabilities that we would like machines to have. The problem is the following: given an image of an object (e.g. someone's face), predict its label (e.g. that person's name) from a set of possible object labels. The predominant approach to solving the recognition problem has been to learn a discriminative model, i.e. a model of the conditional probability P(l|υ) over possible object labels l given an image υ. Here we consider an alternative class of models, broadly referred to as generative models, that learns the latent structure of the image so as to explain how it was generated. This is in contrast to discriminative models, which dedicate their parameters exclusively to representing the conditional distribution P(l|υ). Making finer distinctions among generative models, we consider a supervised generative model of the joint distribution P(υ, l) over image-label pairs, an unsupervised generative model of the distribution P(υ) over images alone, and an unsupervised reconstructive model, which includes models such as autoencoders that can reconstruct a given image, but do not define a proper distribution over images. The goal of this thesis is to empirically demonstrate various ways of using these models for object recognition. Its main conclusion is that such models are not only useful for recognition, but can even outperform purely discriminative models on difficult recognition tasks. We explore four types of applications of generative/reconstructive models for recognition: 1) incorporating complex domain knowledge into the learning by inverting a synthesis model, 2) using the latent image representations of generative/reconstructive models for recognition, 3) optimizing a hybrid generative-discriminative loss function, and 4) creating additional synthetic data for training more accurate discriminative models. Taken together, the results for these applications support the idea that generative/reconstructive models and unsupervised learning have a key role to play in building object recognition systems.

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: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.369
Threshold uncertainty score0.768

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 head0.053
GPT teacher head0.370
Teacher spread0.317 · 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 designBench or experimental
Domainnot available
GenreMethods

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

Citations4
Published2010
Admission routes1
Has abstractyes

Explore more

Same venueTSpaceSame topicImage Retrieval and Classification TechniquesFrench-language works237,207