# Multi-class Object Detection on KITTI 1589 (80/20 evaluation)

Source: [Multi-class Object Detection on KITTI 1589 (80/20 evaluation)](<https://www.sota2.com/research/sota/multi-class-object-detection-on-kitti-1589-80-20-evaluation>)

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

Data updated: 2026-05-11T09:49:37.055Z

Evaluation of Multi-class Object Detection performance on the KITTI 1589 dataset subset using an 80/20 evaluation split, reporting metrics such as Covariance, IoU, and Internal Score.

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 | Multi-class Object Detection |
| Dataset (including any stated split) | KITTI 1589 (80/20 evaluation) |
| Metric | Covariance |
| 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

- [Covariance](<https://www.sota2.com/research/sota/multi-class-object-detection-on-kitti-1589-80-20-evaluation.md?metric=Covariance>): Higher is better; unit: PERCENT.

- [mIoU (%)](<https://www.sota2.com/research/sota/multi-class-object-detection-on-kitti-1589-80-20-evaluation.md?metric=mIoU%20(%25)>): Higher is better; unit: PERCENT.

- [Internal Score](<https://www.sota2.com/research/sota/multi-class-object-detection-on-kitti-1589-80-20-evaluation.md?metric=Internal%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Covariance | Result date | Report paper |
| --- | --- | --- | --- |
| Unscaled CP | 88 | Not recorded | 6a0162b1dbc836b87d823274 |
| Scaled CP | 88 | Not recorded | 6a0162b1dbc836b87d823274 |
| Unscaled CP | 77 | Not recorded | 6a0162b1dbc836b87d823274 |
| Scaled CP | 76 | Not recorded | 6a0162b1dbc836b87d823274 |

### Unscaled CP

Covariance: 88. Result ID: 6a01a57047f34ce924e3ee01.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162b1dbc836b87d823274.md>)

Recorded evaluation configuration: {"alpha":"0.05","alpha\_class":"0.01","pipeline":"two-step"}. This record does not assert independent reproduction.

### Scaled CP

Covariance: 88. Result ID: 6a01a57047f34ce924e3ee03.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162b1dbc836b87d823274.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0162b1dbc836b87d823274.md>)

Recorded evaluation configuration: {"alpha":"0.05","alpha\_class":"0.01","pipeline":"two-step"}. This record does not assert independent reproduction.

### Unscaled CP

Covariance: 77. Result ID: 6a01a57047f34ce924e3ee00.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162b1dbc836b87d823274.md>)

Recorded evaluation configuration: {"alpha":"0.1","alpha\_class":"0.01","pipeline":"two-step"}. This record does not assert independent reproduction.

### Scaled CP

Covariance: 76. Result ID: 6a01a57047f34ce924e3ee02.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162b1dbc836b87d823274.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0162b1dbc836b87d823274.md>)

Recorded evaluation configuration: {"alpha":"0.1","alpha\_class":"0.01","pipeline":"two-step"}. This record does not assert independent reproduction.

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