LLaVA-1.5-7B Fine-Tuning Results on MVTec Zipper Dataset

Christopher Mai published per-fold test results for a fine-tuned LLaVA-1.5-7B model on the MVTec zipper dataset. The 5.5 KB dataset contains metrics reported as percentages, except for the Kappa value. It was last updated on April 29, 2026.

Use Cases

• Benchmarking model performance based on per-fold test results mentioned in the description
• Analyzing fine-tuning outcomes for vision-language models based on reported metrics
• Comparing evaluation metrics like Kappa for anomaly detection models

Strengths

• Dataset is small at 5.5 KB, facilitating quick download and inspection.
• Results are structured per-fold, which may allow for cross-validation analysis.
• Released under a permissive CC-BY-4.0 license.

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

Christopher Mai via figshare

Collection Method

Likely contains evaluation metrics from fine-tuning a vision-language model.

Freshness

Last updated 2026-04-29 17:50:52; freshness should be verified.