# Personalized Object Detection on POD 5-shot

Source: [Personalized Object Detection on POD 5-shot](<https://www.sota2.com/research/sota/personalized-object-detection-on-pod-5-shot>)

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

Data updated: 2026-06-24T07:08:38.119Z

Evaluation of Personalized Object Detection performance on the POD 5-shot dataset configuration, measured using Accuracy.

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 | Personalized Object Detection |
| Dataset (including any stated split) | POD 5-shot |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/personalized-object-detection-on-pod-5-shot.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LLaVa (hi) + CLIP (zV,i) | 80.7 | Not recorded | 68fa7bfc1e209131cea8baaa |
| LLaVa + CLIP + PCA (512) | 80.1 | Not recorded | 68fa7bfc1e209131cea8baaa |
| CLIP (zV,i) | 77.8 | Not recorded | 68fa7bfc1e209131cea8baaa |
| LLaVa (hi) | 72.7 | Not recorded | 68fa7bfc1e209131cea8baaa |
| MOCHA (YOLOv8n) | 45.9 | Not recorded | 68fa7bfc1e209131cea8baaa |

### LLaVa (hi) + CLIP (zV,i)

Accuracy: 80.7. Result ID: 6a3b825afbc373592c4341df.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8baaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Model Category":"Teacher Upper Bound (Frozen VLM features)","Ground-Truth Boxes":"No"}. This record does not assert independent reproduction.

### LLaVa + CLIP + PCA (512)

Accuracy: 80.1. Result ID: 6a3b825afbc373592c4341e0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8baaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Model Category":"Teacher Upper Bound (Frozen VLM features)","Ground-Truth Boxes":"No"}. This record does not assert independent reproduction.

### CLIP (zV,i)

Accuracy: 77.8. Result ID: 6a3b825afbc373592c4341de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8baaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Model Category":"Teacher Upper Bound (Frozen VLM features)","Ground-Truth Boxes":"No"}. This record does not assert independent reproduction.

### LLaVa (hi)

Accuracy: 72.7. Result ID: 6a3b825afbc373592c4341dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8baaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Model Category":"Teacher Upper Bound (Frozen VLM features)","Ground-Truth Boxes":"No"}. This record does not assert independent reproduction.

### MOCHA (YOLOv8n)

Accuracy: 45.9. Result ID: 6a3b825afbc373592c4341e1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8baaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8baaa.md>)

Recorded evaluation configuration: {"Model Category":"Student (Efficient Edge Deployment)","Ground-Truth Boxes":"No"}. This record does not assert independent reproduction.

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