Unverified50% confidenceBenchmarkExact time
The hair shaft counting task is handled by EfficientNet-B5 with a support-map channel, achieving a counting accuracy of 87.0% aligned with expert bounding boxes and a macro-averaged F1 score of 0.85.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe combination of EfficientNet-B3 and SVM achieved the strongest baseline performance, with an accuracy of 96.31% and a macro F1 score of 96.36%.74% similarUnverifiedEfficientNet 从 B0 到 B7，模型参数从 5.3M 增长到 66M，Top-1 精度从 77.1% 提升到 84.3%74% similarUnverifiedIn this task, identifying where a problem occurs (localization F1 generally above 0.78) is much easier than accurately determining the type of problem (label F1 around 0.5).67% similarUnverifiedThe best-performing Edu-QuRater achieved an average accuracy of 0.917 in reproducing GPT-4.1-mini pairwise judgments on the held-out set.66% similarUnverifiedThe Top3 configuration achieved an accuracy of 97.148%, a weighted F1 of 97.055%, and an MCC of 0.9675, comprehensively outperforming the Full21 configuration using all 21 metrics (accuracy 95.999%, weighted F1 95.521%, MCC 0.9549).65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975925API
curl https://kongchang.com/api/v1/knowledge/claims/975925MCP
get_claim(id=975925)