SmartTrim Threshold Sensitivity Analysis Averaged Across Three Medical Imaging Datasets

5.5 KB of tabular data from Chong Liu analyzes the sensitivity of a pruning algorithm's threshold adjustment coefficient. The data likely contains averaged performance metrics from three medical imaging datasets: COVID-19, ISIC, and ChestX-ray14 Extended. The dataset was last updated on April 24, 2026.

Use Cases

• Evaluate pruning algorithm robustness based on averaged performance across multiple datasets
• Analyze the relationship between pruning intensity and model performance based on the threshold adjustment coefficient
• Benchmark pruning methods using aggregated results from COVID-19, ISIC, and ChestX-ray14 datasets

Strengths

• Data is aggregated from three distinct medical imaging datasets, providing a multi-source perspective.
• The dataset is licensed under CC-BY-4.0, allowing for open reuse and redistribution.
• The file size is 5.5 KB, indicating a compact and focused dataset.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare

Collection Method

Data are described as the average values of three datasets.

Freshness

Last updated 2026-04-24 17:35:38; freshness should be verified.