# Object Detection on PASCAL VOC Split 1 1-shot 2007 (test)

Source: [Object Detection on PASCAL VOC Split 1 1-shot 2007 (test)](<https://www.sota2.com/research/sota/object-detection-on-pascal-voc-split-1-1-shot-2007-test>)

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

Data updated: 2026-02-26T05:37:37.333Z

Evaluation of 1-shot Object Detection performance on the PASCAL VOC 2007 test set using the Split 1 configuration, reporting Base AP50 and Novel AP50 scores.

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) | PASCAL VOC Split 1 1-shot 2007 (test) |
| Metric | Base AP50 |
| 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

- [Base AP50](<https://www.sota2.com/research/sota/object-detection-on-pascal-voc-split-1-1-shot-2007-test.md?metric=Base%20AP50>): Higher is better; unit: PERCENT.

- [Novel AP50](<https://www.sota2.com/research/sota/object-detection-on-pascal-voc-split-1-1-shot-2007-test.md?metric=Novel%20AP50>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Base AP50 | Result date | Report paper |
| --- | --- | --- | --- |
| TFA w/ cos | 79.1 | Not recorded | 68fa697a1e209131cea224d4 |
| FSCE | 78.9 | Not recorded | 68fa697a1e209131cea224d4 |
| MPSR | 59.4 | Not recorded | 68fa697a1e209131cea224d4 |
| Baseline-FPN | 56.9 | Not recorded | 68fa697a1e209131cea224d4 |

### TFA w/ cos

Base AP50: 79.1. Result ID: 698dacb98b517eb433230ae0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea224d4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67341e209131cea14b81.md>)

[Implementation](<https://github.com/ucbdrive/few-shot-object-detection>)

Recorded evaluation configuration: {"implementation":"our implementation","classifier":"cosine similarity"}. This record does not assert independent reproduction.

### FSCE

Base AP50: 78.9. Result ID: 698dacb98b517eb433230ae1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea224d4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea224d4.md>)

[Implementation](<https://github.com/MegviiDetection/FSCE>)

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

### MPSR

Base AP50: 59.4. Result ID: 698dacb98b517eb433230adf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea224d4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67f21e209131cea194b6.md>)

[Implementation](<https://github.com/jiaxi-wu/MPSR>)

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

### Baseline-FPN

Base AP50: 56.9. Result ID: 698dacb98b517eb433230ade.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea224d4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67f21e209131cea194b6.md>)

[Implementation](<https://github.com/jiaxi-wu/MPSR>)

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

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