# Vehicle Detection on RADIal (test)

Source: [Vehicle Detection on RADIal (test)](<https://www.sota2.com/research/sota/vehicle-detection-on-radial-test>)

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

Data updated: 2026-05-13T07:43:40.459Z

Evaluation of Vehicle Detection performance on the test split of the RADIal dataset, reporting accuracy metrics (AP, AR, F1), localization errors (RE, AE), and hardware efficiency metrics (FPS, Model Size, GPU Cost).

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 | Vehicle Detection |
| Dataset (including any stated split) | RADIal (test) |
| Metric | AP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [AP](<https://www.sota2.com/research/sota/vehicle-detection-on-radial-test.md?metric=AP>): Higher is better; unit: PERCENT.

- [AR](<https://www.sota2.com/research/sota/vehicle-detection-on-radial-test.md?metric=AR>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/vehicle-detection-on-radial-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Localization Error (RE) (m)](<https://www.sota2.com/research/sota/vehicle-detection-on-radial-test.md?metric=Localization%20Error%20(RE)%20(m)>): Lower is better; unit: OTHER.

- [Angular Error (AE) (°)](<https://www.sota2.com/research/sota/vehicle-detection-on-radial-test.md?metric=Angular%20Error%20(AE)%20(%C2%B0)>): Lower is better; unit: OTHER.

- [Parameters (M)](<https://www.sota2.com/research/sota/vehicle-detection-on-radial-test.md?metric=Parameters%20(M)>): Lower is better; unit: SIZE.

- [FPS](<https://www.sota2.com/research/sota/vehicle-detection-on-radial-test.md?metric=FPS>): Higher is better; unit: SCALAR.

- [FPS Jitter (σ)](<https://www.sota2.com/research/sota/vehicle-detection-on-radial-test.md?metric=FPS%20Jitter%20(%CF%83)>): Lower is better; unit: SCALAR.

- [Model Size](<https://www.sota2.com/research/sota/vehicle-detection-on-radial-test.md?metric=Model%20Size>): Lower is better; unit: SIZE.

- [GPU Cost](<https://www.sota2.com/research/sota/vehicle-detection-on-radial-test.md?metric=GPU%20Cost>): Lower is better; unit: OTHER.

## Recorded results

| Method | AP | Result date | Report paper |
| --- | --- | --- | --- |
| EchoFusion | 96.95 | Not recorded | 68fa75d41e209131cea6a17d |
| CMS | 96.9 | Not recorded | 68fa75d41e209131cea6a17d |
| REFNet | 95.75 | Not recorded | 68fa75d41e209131cea6a17d |
| ADCNet | 95 | Not recorded | 68fa75d41e209131cea6a17d |
| FFTRadNet | 93.45 | Not recorded | 68fa75d41e209131cea6a17d |
| ROFusion | 91.13 | Not recorded | 68fa75d41e209131cea6a17d |
| TFFTRadNet | 90.8 | Not recorded | 68fa75d41e209131cea6a17d |

### EchoFusion

AP: 96.95. Result ID: 6a042b6147f34ce924e9c884.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d41e209131cea6a17d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa712b1e209131cea4faad.md>)

[Implementation](<https://github.com/tusen-ai/EchoFusion>)

Recorded evaluation configuration: {"Modality":"RT&C"}. This record does not assert independent reproduction.

### CMS

AP: 96.9. Result ID: 6a042b6147f34ce924e9c882.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d41e209131cea6a17d.md>)

Recorded evaluation configuration: {"Modality":"RD&C"}. This record does not assert independent reproduction.

### REFNet

AP: 95.75. Result ID: 6a042b6147f34ce924e9c885.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d41e209131cea6a17d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d41e209131cea6a17d.md>)

Recorded evaluation configuration: {"Modality":"RD&C"}. This record does not assert independent reproduction.

### ADCNet

AP: 95. Result ID: 6a042b6147f34ce924e9c881.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d41e209131cea6a17d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51966.md>)

Recorded evaluation configuration: {"Modality":"ADC"}. This record does not assert independent reproduction.

### FFTRadNet

AP: 93.45. Result ID: 6a042b6147f34ce924e9c87f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d41e209131cea6a17d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c391e209131cea32e49.md>)

Recorded evaluation configuration: {"Modality":"RD","Detection-only head configuration":"true"}. This record does not assert independent reproduction.

### ROFusion

AP: 91.13. Result ID: 6a042b6147f34ce924e9c883.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d41e209131cea6a17d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70061e209131cea48a97.md>)

Recorded evaluation configuration: {"Modality":"RD&RPC&C"}. This record does not assert independent reproduction.

### TFFTRadNet

AP: 90.8. Result ID: 6a042b6147f34ce924e9c880.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d41e209131cea6a17d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee41e209131cea42b10.md>)

Recorded evaluation configuration: {"Modality":"ADC","Detection-only head configuration":"true"}. This record does not assert independent reproduction.

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