khornlund/severstal-steel-defect-detection
Kaggle Segmentation Challenge
Implements an ensemble of EfficientNet and SE-ResNeXt encoders paired with FPN/U-Net decoders using the segmentation_models.pytorch framework to detect and classify four types of surface defects on steel sheets. Training leverages mixed loss (0.6 BCE + 0.4 Dice), pseudo-labeling with balanced sampling, and grayscale input adaptation via weight recycling to achieve diverse model predictions. Achieves 0.91023 private leaderboard score through careful hyperparameter tuning, encoder/decoder architecture exploration, and image augmentation via Albumentations.
263 stars. No commits in the last 6 months.
Stars
263
Forks
58
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 07, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/khornlund/severstal-steel-defect-detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
RajdeepBiswas/Manufacturing-Quality-Inspection
I have built the computer vision models in 3 different ways addressing different personas,...
huangyebiaoke/steel-pipe-weld-defect-detection
Deep Learning Based Steel Pipe Weld Defect Detection
LukeVassallo/RL_PCB
RL_PCB is a novel learning-based method for optimising the placement of circuit components on a...
utkarsh-ankit/Defect-Detection-of-PCB
A repository for creating a Deep Learning model for Defect Detection in PCBs and to design a Web...
siddhartamukherjee/NEU-DET-Steel-Surface-Defect-Detection
This project is about detecting defects on steel surface using Unet. The dataset used for this...