DualFusionNet vs. LLaVA-1.5-7B Performance on the MVTec Zipper Dataset

A 5.5 KB Excel file compares the performance of DualFusionNet and a fine-tuned LLaVA-1.5-7B model on the MVTec zipper dataset. Results are reported as mean ± standard deviation across five cross-validation folds, with metrics in percentages except for Kappa. The dataset was authored by Christopher Mai and last updated on April 29, 2026.

Use Cases

• Benchmark anomaly detection models based on reported performance metrics.
• Compare vision-language model fine-tuning against specialized architectures based on the described evaluation.
• Analyze model robustness based on cross-validation results mentioned in the description.

Strengths

• Results are aggregated over five cross-validation folds, suggesting a measure of statistical reliability.
• Metrics are clearly defined as percentages, except for Kappa, providing a standard evaluation framework.
• Dataset is small (5.5 KB), facilitating quick download and inspection.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is limited to a single object category (zipper) from the MVTec AD benchmark.

Provenance

Source

figshare

Collection Method

Likely contains experimental results from model evaluation.

Freshness

Last updated 2026-04-29 17:50:51; freshness should be verified.