IdeaCredIdeaCred

robertbejan/cotraining_dissertation

50

This project is a Deep Learning approach at medical image classification. This is mainly focused on developing a semi-supervised learning algorithm based on co-training and pseudo-labeling. This serves as the final project for my master's thesis and it's still under development.

What's novel

This project is a Deep Learning approach at medical image classification. This is mainly focused on developing a semi-supervised learning algorithm based on co-training and pseudo-labeling. This serves as the final project for my master's thesis and it's still under development.

Code Analysis

9 files read · 3 rounds

Implements Blum & Mitchell co-training for fetal ultrasound plane classification using two views: a grayscale SqueezeNet CNN and a DINOv2+FFT autoencoder+XGBoost ensemble, with joint pseudo-labeling, adaptive confidence thresholds, and reevaluation-based sample removal.

Strengths

The co-training algorithm is genuinely implemented with non-trivial logic: joint pseudo-labeling requiring model agreement, adaptive threshold adjustment based on rolling removal rates, and hash-based deduplication of pseudo-samples. The hybrid ensemble (frozen DINOv2 + FFT features + autoencoder + XGBoost) is a creative multi-modal approach for the frequency-domain view.

Weaknesses

Critical bugs exist (undefined `self` in module-level function, MLflow context manager exited before training), zero tests, hardcoded paths throughout, no model loading capability, and the project structure is a flat directory of scripts with temp files and a 952KB SQLite DB committed to the repo. The FFT ensemble is only trained once at epoch 1 and never updated, undermining the co-training premise for that branch.

Score Breakdown

Innovation
6 (25%)
Craft
34 (35%)
Traction
6 (15%)
Scope
59 (25%)

Signal breakdown

Innovation

Not Fork+1
Code Novelty+1
Concept Novelty+2

Craft

Ci-1
Tests-1
Polish+0
Releases+0
Has License+0
Code Quality+11
Readme Quality+12
Recent Activity+7
Structure Quality+4
Commit Consistency+2
Has Dependency Mgmt+0

Traction

Forks+0
Stars+6
Hn Points+0
Watchers+0
Early Traction+0
Devto Reactions+0
Community Contribs+0

Scope

Commits+7
Languages+5
Subsystems+5
Bloat Penalty+0
Completeness+5
Contributors+5
Authored Files+12
Readme Code Match+3
Architecture Depth+3
Implementation Depth+8

Evidence

Commits

30

Contributors

1

Files

67

Active weeks

4

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

2

Forks

0

License