SSH-YOLO: Object Detection Model Performance Comparison Results

A 5.5 KB Excel file uploaded on 2026-04-15 by Tenglong Ma. It contains performance metrics for the SSH-YOLO object detection model, comparing it against baseline models like YOLOv8n on several datasets. The results include [email protected] scores for the RoadScene-Complex, BDD100K, KITTI, COCO small target subset, and CityPersons datasets.

Use Cases

• Benchmarking object detection models for small targets (< 32x32 pixels) based on the described four-level detection system.
• Evaluating model performance on occluded objects based on the spatial and channel collaborative attention module (SCSA) results.
• Comparing inference speed and accuracy trade-offs for real-time on-board detection based on the reported 60 FPS metric.
• Analyzing model improvements for dense targets in complex road scenarios based on the reported [email protected] gains.

Strengths

• Provides specific [email protected] performance gains, such as a 12.4% increase over YOLOv8n on the RoadScene-Complex dataset.
• Reports inference speed of up to 60 FPS, indicating suitability for real-time applications.
• Results are compared across multiple public datasets (BDD100K, KITTI, COCO, CityPersons) and a self-built dataset.

Limitations

• Row count and specific column-level documentation are absent; field semantics must be inferred after download.
• The dataset is very small (5.5 KB), suggesting it contains summary results rather than raw detection data or annotations.

Provenance

Source

Tenglong Ma via figshare.

Collection Method

Likely contains experimental results from training and evaluating the SSH-YOLO model.

Freshness

Last updated 2026-04-15 18:05:45; freshness should be verified.