# Object Detection on Locomotive coil spring defect dataset (test)

Source: [Object Detection on Locomotive coil spring defect dataset (test)](<https://www.sota2.com/research/sota/object-detection-on-locomotive-coil-spring-defect-dataset-test>)

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

Data updated: 2026-03-17T08:02:59.533Z

Evaluation of Object Detection performance on the test split of the Locomotive coil spring defect dataset, reporting standard detection metrics like mAP.

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) | Locomotive coil spring defect dataset (test) |
| Metric | mAP@0.5 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [mAP@0.5](<https://www.sota2.com/research/sota/object-detection-on-locomotive-coil-spring-defect-dataset-test.md?metric=mAP%400.5>): Higher is better; unit: PERCENT.

- [mAP@0.5:0.95](<https://www.sota2.com/research/sota/object-detection-on-locomotive-coil-spring-defect-dataset-test.md?metric=mAP%400.5%3A0.95>): Higher is better; unit: PERCENT.

- [AP\_S](<https://www.sota2.com/research/sota/object-detection-on-locomotive-coil-spring-defect-dataset-test.md?metric=AP_S>): Higher is better; unit: PERCENT.

- [AP\_M](<https://www.sota2.com/research/sota/object-detection-on-locomotive-coil-spring-defect-dataset-test.md?metric=AP_M>): Higher is better; unit: PERCENT.

- [AP\_L](<https://www.sota2.com/research/sota/object-detection-on-locomotive-coil-spring-defect-dataset-test.md?metric=AP_L>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP@0.5 | Result date | Report paper |
| --- | --- | --- | --- |
| MSD-DETR | 92.4 | Not recorded | 69b8e00b0636e5bf4afbea21 |
| RT-DETR-L | 89.1 | Not recorded | 69b8e00b0636e5bf4afbea21 |
| DINO | 88.9 | Not recorded | 69b8e00b0636e5bf4afbea21 |
| YOLOv8-L | 88.2 | Not recorded | 69b8e00b0636e5bf4afbea21 |
| YOLOv7 | 87.4 | Not recorded | 69b8e00b0636e5bf4afbea21 |
| YOLOv5-L | 86.7 | Not recorded | 69b8e00b0636e5bf4afbea21 |
| Deformable DETR | 85.4 | Not recorded | 69b8e00b0636e5bf4afbea21 |
| Faster R-CNN | 82.3 | Not recorded | 69b8e00b0636e5bf4afbea21 |
| DETR | 79.8 | Not recorded | 69b8e00b0636e5bf4afbea21 |

### MSD-DETR

mAP@0.5: 92.4. Result ID: 69b90aa847f34ce924a1620b.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00b0636e5bf4afbea21.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e00b0636e5bf4afbea21.md>)

Recorded evaluation configuration: {"Params(M)":"34.2","FLOPs(G)":"112.5","FPS":"98","Latency(ms)":"10.2"}. This record does not assert independent reproduction.

### RT-DETR-L

mAP@0.5: 89.1. Result ID: 69b90aa847f34ce924a1620a.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00b0636e5bf4afbea21.md>)

Recorded evaluation configuration: {"Params(M)":"32.0","FLOPs(G)":"108.0","FPS":"114","Latency(ms)":"8.8"}. This record does not assert independent reproduction.

### DINO

mAP@0.5: 88.9. Result ID: 69b90aa847f34ce924a16209.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00b0636e5bf4afbea21.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777c1e209131cea7380c.md>)

Recorded evaluation configuration: {"Params(M)":"47.0","FLOPs(G)":"279.0","FPS":"21","Latency(ms)":"47.6"}. This record does not assert independent reproduction.

### YOLOv8-L

mAP@0.5: 88.2. Result ID: 69b90aa847f34ce924a16206.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00b0636e5bf4afbea21.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78451e209131cea7784e.md>)

Recorded evaluation configuration: {"Params(M)":"43.7","FLOPs(G)":"165.2","FPS":"78","Latency(ms)":"12.8"}. This record does not assert independent reproduction.

### YOLOv7

mAP@0.5: 87.4. Result ID: 69b90aa847f34ce924a16205.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00b0636e5bf4afbea21.md>)

Recorded evaluation configuration: {"Params(M)":"36.9","FLOPs(G)":"104.7","FPS":"78","Latency(ms)":"12.8"}. This record does not assert independent reproduction.

### YOLOv5-L

mAP@0.5: 86.7. Result ID: 69b90aa847f34ce924a16204.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00b0636e5bf4afbea21.md>)

Recorded evaluation configuration: {"Params(M)":"46.5","FLOPs(G)":"109.1","FPS":"82","Latency(ms)":"12.2"}. This record does not assert independent reproduction.

### Deformable DETR

mAP@0.5: 85.4. Result ID: 69b90aa847f34ce924a16208.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00b0636e5bf4afbea21.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b41e209131cea580c8.md>)

Recorded evaluation configuration: {"Params(M)":"40.0","FLOPs(G)":"78.0","FPS":"42","Latency(ms)":"23.8"}. This record does not assert independent reproduction.

### Faster R-CNN

mAP@0.5: 82.3. Result ID: 69b90aa847f34ce924a16203.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00b0636e5bf4afbea21.md>)

Recorded evaluation configuration: {"Params(M)":"41.5","FLOPs(G)":"180.2","FPS":"18","Latency(ms)":"55.6"}. This record does not assert independent reproduction.

### DETR

mAP@0.5: 79.8. Result ID: 69b90aa847f34ce924a16207.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e00b0636e5bf4afbea21.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b51e209131cea5810f.md>)

Recorded evaluation configuration: {"Params(M)":"41.0","FLOPs(G)":"86.0","FPS":"25","Latency(ms)":"40.0"}. This record does not assert independent reproduction.

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