# Object Detection on ImageNet 5 supports (50 novel categories)

Source: [Object Detection on ImageNet 5 supports (50 novel categories)](<https://www.sota2.com/research/sota/object-detection-on-imagenet-5-supports-50-novel-categories>)

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

Data updated: 2026-02-26T05:23:16.840Z

Evaluation of Object Detection performance on the ImageNet 5 supports subset, focusing on 50 novel categories, typically measured using Average Precision metrics (AP50, AP75).

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) | ImageNet 5 supports (50 novel categories) |
| Metric | AP50 |
| 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

- [AP50](<https://www.sota2.com/research/sota/object-detection-on-imagenet-5-supports-50-novel-categories.md?metric=AP50>): Higher is better; unit: PERCENT.

- [AP75](<https://www.sota2.com/research/sota/object-detection-on-imagenet-5-supports-50-novel-categories.md?metric=AP75>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP50 | Result date | Report paper |
| --- | --- | --- | --- |
| Ours | 44.1 | Not recorded | 68fa67901e209131cea170c4 |
| Ours | 41.7 | Not recorded | 68fa67901e209131cea170c4 |
| Ours | 41.3 | Not recorded | 68fa67901e209131cea170c4 |
| RepMet | 39.6 | Not recorded | 68fa67901e209131cea170c4 |
| LSTD | 31.4 | Not recorded | 68fa67901e209131cea170c4 |

### Ours

AP50: 44.1. Result ID: 698d3b228b517eb4331ff56a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67901e209131cea170c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67901e209131cea170c4.md>)

[Implementation](<https://github.com/fanq15/Few-Shot-Object-Detection-Dataset>)

Recorded evaluation configuration: {"dataset":"FSOD†","fine-tune":"ImageNet"}. This record does not assert independent reproduction.

### Ours

AP50: 41.7. Result ID: 698d3b228b517eb4331ff569.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67901e209131cea170c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67901e209131cea170c4.md>)

[Implementation](<https://github.com/fanq15/Few-Shot-Object-Detection-Dataset>)

Recorded evaluation configuration: {"dataset":"FSOD†","fine-tune":"None"}. This record does not assert independent reproduction.

### Ours

AP50: 41.3. Result ID: 698d3b228b517eb4331ff568.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67901e209131cea170c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67901e209131cea170c4.md>)

[Implementation](<https://github.com/fanq15/Few-Shot-Object-Detection-Dataset>)

Recorded evaluation configuration: {"dataset":"COCO","fine-tune":"ImageNet"}. This record does not assert independent reproduction.

### RepMet

AP50: 39.6. Result ID: 698d3b228b517eb4331ff567.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67901e209131cea170c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65121e209131cea07fa4.md>)

Recorded evaluation configuration: {"dataset":"COCO","fine-tune":"ImageNet"}. This record does not assert independent reproduction.

### LSTD

AP50: 31.4. Result ID: 698d3b228b517eb4331ff566.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67901e209131cea170c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64241e209131cea02c96.md>)

Recorded evaluation configuration: {"dataset":"COCO","fine-tune":"ImageNet"}. This record does not assert independent reproduction.

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