# Object Detection on MMFW-UAV Wide modality (five cross-validation folds)

Source: [Object Detection on MMFW-UAV Wide modality (five cross-validation folds)](<https://www.sota2.com/research/sota/object-detection-on-mmfw-uav-wide-modality-five-cross-validation-folds>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-10T12:42:17.050Z

Evaluation of Object Detection performance on the MMFW-UAV Wide modality dataset using five cross-validation folds, reporting standard detection metrics (mAP50, mAP50-95) and efficiency metrics (Latency, FPS).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Object Detection |
| Dataset (including any stated split) | MMFW-UAV Wide modality (five cross-validation folds) |
| Metric | Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Precision](<https://www.sota2.com/research/sota/object-detection-on-mmfw-uav-wide-modality-five-cross-validation-folds.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/object-detection-on-mmfw-uav-wide-modality-five-cross-validation-folds.md?metric=Recall>): Higher is better; unit: PERCENT.

- [mAP50](<https://www.sota2.com/research/sota/object-detection-on-mmfw-uav-wide-modality-five-cross-validation-folds.md?metric=mAP50>): Higher is better; unit: PERCENT.

- [mAP50-95](<https://www.sota2.com/research/sota/object-detection-on-mmfw-uav-wide-modality-five-cross-validation-folds.md?metric=mAP50-95>): Higher is better; unit: PERCENT.

- [Latency (ms/img)](<https://www.sota2.com/research/sota/object-detection-on-mmfw-uav-wide-modality-five-cross-validation-folds.md?metric=Latency%20(ms%2Fimg)>): Lower is better; unit: TIME.

- [FPS](<https://www.sota2.com/research/sota/object-detection-on-mmfw-uav-wide-modality-five-cross-validation-folds.md?metric=FPS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| Yolov10x | 96.1 | Not recorded | 69afa5ba2d603e6de3e43e50 |
| Yolov10x | 94.06 | Not recorded | 69afa5ba2d603e6de3e43e50 |
| Yolov12x | 92.16 | Not recorded | 69afa5ba2d603e6de3e43e50 |
| Yolov9e | 91.2 | Not recorded | 69afa5ba2d603e6de3e43e50 |

### Yolov10x

Precision: 96.1. Result ID: 69b011936dbb7075b959fe56.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5ba2d603e6de3e43e50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75761e209131cea681be.md>)

[Implementation](<https://github.com/THU-MIG/yolov10>)

Recorded evaluation configuration: {"Architecture":"Yolov10x","Experiment":"Wide (fine-tuned)","fine-tuned":"true"}. This record does not assert independent reproduction.

### Yolov10x

Precision: 94.06. Result ID: 69b011936dbb7075b959fe55.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5ba2d603e6de3e43e50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75761e209131cea681be.md>)

[Implementation](<https://github.com/THU-MIG/yolov10>)

Recorded evaluation configuration: {"Architecture":"Yolov10x","Experiment":"Wide"}. This record does not assert independent reproduction.

### Yolov12x

Precision: 92.16. Result ID: 69b011936dbb7075b959fe54.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5ba2d603e6de3e43e50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77021e209131cea70735.md>)

Recorded evaluation configuration: {"Architecture":"Yolov12x","Experiment":"Wide"}. This record does not assert independent reproduction.

### Yolov9e

Precision: 91.2. Result ID: 69b011936dbb7075b959fe53.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5ba2d603e6de3e43e50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72561e209131cea55bdf.md>)

[Implementation](<https://github.com/WongKinYiu/yolov9>)

Recorded evaluation configuration: {"Architecture":"Yolov9e","Experiment":"Wide"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.