YOLO Variants Performance on Validation Set

Avinash Bansal published this 5.5 KB Excel file on April 21, 2026. It contains performance metrics for additional YOLO (You Only Look Once) object detection model variants on a validation set. The parameters used for evaluation are consistent with those referenced in a linked academic table.

Use Cases

• Benchmarking YOLO model variants based on reported performance metrics.
• Analyzing the impact of architectural changes in object detection models based on the comparative results.
• Selecting a YOLO variant for a specific application based on its validation set performance.

Strengths

• File size is 5.5 KB, making it quick to download and inspect.
• Published under a permissive CC-BY-4.0 license, allowing for reuse and redistribution.
• Evaluation parameters are documented as being consistent with a referenced academic source.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare, author Avinash Bansal

Collection Method

Likely contains results from model evaluation experiments.

Time Range

The dataset itself was last updated in 2026; the temporal coverage of the underlying validation data is unknown.

Freshness

Last updated 2026-04-21 17:44:23; freshness should be verified.

Geography

Spatial coverage is not specified.