SSH-YOLO: Object Detection Model Performance Comparison Results

A 5.5 KB Excel file containing performance metrics for the SSH-YOLO object detection model. The dataset, authored by Tenglong Ma and last updated in April 2026, presents comparison results against YOLOv8n on multiple datasets, including a self-built RoadScene-Complex dataset and public datasets like BDD100K, KITTI, COCO, and CityPersons.

Use Cases

• Benchmarking object detection models based on reported [email protected] scores.
• Evaluating model performance on small targets based on the described 160x160 detection head.
• Comparing detection accuracy in occluded scenes based on results from the CityPersons dataset.
• Assessing the trade-off between inference speed and accuracy based on the reported 60 FPS metric.

Strengths

• Performance metrics are provided for multiple standard datasets (BDD100K, KITTI, COCO, CityPersons).
• Specific [email protected] improvement percentages are reported (e.g., 12.4% higher than YOLOv8n).
• The model's inference speed of 60 FPS is quantified.

Limitations

• The dataset is very small (5.5 KB), suggesting limited scope or summary-level data only.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

figshare

Collection Method

Likely contains experimental results from model training and evaluation.

Freshness

Last updated 2026-04-15 18:05:47; freshness should be verified.