# Object Detection on Visual Genome LVIS -\> VisualGenome transfer (val)

Source: [Object Detection on Visual Genome LVIS -\> VisualGenome transfer (val)](<https://www.sota2.com/research/sota/object-detection-on-visual-genome-lvis-visualgenome-transfer-val>)

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

Data updated: 2026-02-27T07:45:24.062Z

Evaluation of Object Detection performance using a transfer setup between LVIS and Visual Genome datasets on the validation split, reporting metrics for all, known, and novel categories.

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) | Visual Genome LVIS -\> VisualGenome transfer (val) |
| Metric | mAP (all) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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 (all)](<https://www.sota2.com/research/sota/object-detection-on-visual-genome-lvis-visualgenome-transfer-val.md?metric=mAP%20(all)>): Higher is better; unit: PERCENT.

- [mAP (known)](<https://www.sota2.com/research/sota/object-detection-on-visual-genome-lvis-visualgenome-transfer-val.md?metric=mAP%20(known)>): Higher is better; unit: PERCENT.

- [mAP (novel)](<https://www.sota2.com/research/sota/object-detection-on-visual-genome-lvis-visualgenome-transfer-val.md?metric=mAP%20(novel)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP (all) | Result date | Report paper |
| --- | --- | --- | --- |
| Fully-supervised | 4.52 | Not recorded | 68fa6e1d1e209131cea3ddfd |
| RNCDL | 4.46 | Not recorded | 68fa6e1d1e209131cea3ddfd |
| RNCDL | 2.13 | Not recorded | 68fa6e1d1e209131cea3ddfd |

### Fully-supervised

mAP (all): 4.52. Result ID: 69a14b8935dfcabb00e6141c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e1d1e209131cea3ddfd.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RNCDL

mAP (all): 4.46. Result ID: 69a14b8935dfcabb00e6141b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e1d1e209131cea3ddfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e1d1e209131cea3ddfd.md>)

[Implementation](<https://github.com/vlfom/RNCDL>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RNCDL

mAP (all): 2.13. Result ID: 69a14b8935dfcabb00e6141a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e1d1e209131cea3ddfd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e1d1e209131cea3ddfd.md>)

[Implementation](<https://github.com/vlfom/RNCDL>)

Recorded evaluation configuration: {"initialization":"random init."}. This record does not assert independent reproduction.

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