Table 4: Object Detection Model Performance Metrics

Table 4 contains performance metrics for the SSH-YOLO object detection model, as reported in the associated research paper. The data, authored by Tenglong Ma, was last updated on April 15, 2026. It is a small, 5.5 KB Excel file.

Use Cases

• Benchmarking object detection models based on reported [email protected] scores.
• Comparing model performance on small targets (< 32x32 pixels) based on the description of a dedicated detection head.
• Evaluating detection accuracy in occluded scenarios based on the described spatial and channel collaborative attention module.
• Assessing the trade-off between model accuracy and inference speed based on the reported 60 FPS metric.

Strengths

• Performance metrics are directly comparable to the YOLOv8n baseline model, with specific percentage improvements reported.
• The dataset is licensed under CC-BY-4.0, allowing for open sharing and reuse.
• The associated research paper provides a detailed methodological context for the data.

Limitations

• The dataset is very small (5.5 KB), suggesting it contains only summary statistics, not raw training or validation data.
• Column-level documentation is absent; field semantics must be inferred from the paper.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Tenglong Ma via figshare

Collection Method

Likely contains experimental results from model evaluation on the RoadScene-Complex, BDD100K, KITTI, COCO, and CityPersons datasets.

Freshness

Last updated 2026-04-15 18:05:42; freshness should be verified.