Tabulated detection results generated by the Single Shot MultiBox Detector (SSD) architecture. The 91.6 KB CSV file contains predicted bounding box coordinates, class labels, and associated confidence scores. Author Lin Lin uploaded the dataset under a CC-BY-4.0 license on figshare, with a last update timestamp of 2026-05-07.
Use Cases
- Analyze model performance metrics based on predicted bounding box coordinates and confidence scores.
- Compare detection accuracy across object classes based on the provided class labels.
- Use the structured predictions as a benchmark or baseline for new object detection architectures.
Strengths
- Data is structured as a 91.6 KB CSV file, facilitating easy programmatic access.
- Predictions include three core components for object detection: bounding boxes, class labels, and confidence scores.
- Dataset is openly licensed under CC-BY-4.0, permitting reuse and redistribution.
Limitations
- Row count is unknown, which may limit suitability assessment for large-scale training.
- 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
- figshare
- Collection Method
- Generated by the Single Shot MultiBox Detector (SSD) architecture.
- Time Range
- null
- Freshness
- Last updated 2026-05-07 18:00:04; freshness should be verified.
- Geography
- null