CMAP-Fusion Ablation Study Results on ChestX-ray14 Extended Dataset

Ablation study results for the CMAP-Fusion model on the ChestX-ray14 Extended Dataset. The data likely contains metrics comparing the impact of ViT-B/16, SmartTrim, and CMT modules on classification performance and efficiency. The dataset was authored by Chong Liu and last updated on April 24, 2026.

Use Cases

• Compare the impact of different architectural modules on model accuracy based on the ablation study.
• Analyze trade-offs between model performance and computational efficiency based on metrics like FLOPs and parameters.
• Evaluate cross-modal similarity and feature sparsity in a multimodal fusion model.
• Benchmark classification performance using metrics like AUC, F1 Score, and Kappa.

Strengths

• Provides a direct comparison of three specific modules (ViT-B/16, SmartTrim, CMT) on a medical imaging dataset.
• Includes multiple performance and efficiency metrics (accuracy, F1, AUC, Kappa, parameters, FLOPs, sparsity, similarity).
• Dataset is openly licensed under CC-BY-4.0.

Limitations

• Row count and column-level documentation are unknown, limiting suitability assessment.
• The dataset is very small (5.5 KB), suggesting limited scope or summary-level results.
• Description metadata is limited; actual data structure requires manual inspection after download.

Provenance

Source

figshare

Freshness

Last updated 2026-04-24 17:35:37; freshness should be verified.