Steel Defect Detection Model Benchmark Results

A collection of benchmark results for steel defect detection models, focusing on performance metrics. It is a small dataset of 5.5 KB in XLS format, authored by Aping Ge and last updated in March 2026.

Use Cases

• Compare detection accuracy metrics across models for Severstal steel defect datasets.
• Analyze the relationship between computational cost and performance for models using kernel convolution or residual learning.
• Evaluate model adaptability and performance on diverse defect scales as indicated by the benchmark tags.

Strengths

• Dataset is openly licensed under CC BY 4.0.
• Provides a focused benchmark specifically for steel defect detection models.
• Includes results from models addressing diverse defect scales and frequency awareness.

Limitations

• The dataset is very small at 5.5 KB, indicating limited scope and likely a summary of results rather than raw data.
• No column names or sample data are provided, limiting understanding of the specific metrics and structure.
• The future last updated date of 2026-03-20 suggests the metadata may be incorrect or provisional.

Provenance

Source

figshare, authored by Aping Ge.

Collection Method

Benchmarking results from model evaluations.

Freshness

Last updated 2026-03-20.