Lightweight YOLO-Mamba: Infrared-Visible Small Object Detection Performance Metrics

Performance metrics for a lightweight multimodal object detection framework designed for unmanned aerial vehicle (UAV) scenes. The dataset, authored by zedong huang and last updated on 2026-04-24, contains results from experiments on the LLVIP and DroneVehicle datasets. It likely includes model performance scores, computational metrics, and comparative analysis data.

Use Cases

• Benchmarking lightweight object detection models based on reported mAP and computational efficiency metrics.
• Analyzing model robustness in low-light and foggy conditions based on the described experimental results.
• Evaluating multimodal fusion strategies for infrared and visible imagery based on the described gated adaptive fusion method.

Strengths

• Model performance is quantified with specific metrics: 89.3% [email protected], 11.2 M parameters, and 19.7 GFLOPs.
• Experiments were conducted on two established datasets: LLVIP and DroneVehicle.
• The dataset is shared under a permissive CC-BY-4.0 license.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The 39.0 KB file size suggests a very limited scope, likely containing summary results rather than raw image data.

Provenance

Source

figshare

Collection Method

Results from comprehensive experiments on the LLVIP and DroneVehicle datasets, as described in the associated paper.

Time Range

null

Freshness

Last updated 2026-04-24 15:37:27; freshness should be verified.

Geography

null