# Object Detection on PASCAL VOC (AP50)

Source: [Object Detection on PASCAL VOC (AP50)](<https://www.sota2.com/research/sota/object-detection-on-pascal-voc-ap50>)

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

Data updated: 2026-02-26T05:23:25.182Z

Evaluation of Object Detection performance on the PASCAL VOC dataset, reporting the Average Precision score calculated at an Intersection over Union (IoU) threshold of 0.50.

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 |
| Metric | AP@50 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [AP@50](<https://www.sota2.com/research/sota/object-detection-on-pascal-voc-ap50.md?metric=AP%4050>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP@50 | Result date | Report paper |
| --- | --- | --- | --- |
| CoKe | 83.2 | Not recorded | 68fa6c1d1e209131cea32507 |
| MoCo-v2 | 83 | Not recorded | 68fa6c1d1e209131cea32507 |
| BYOL | 82.9 | Not recorded | 68fa6c1d1e209131cea32507 |
| SwAV | 82.1 | Not recorded | 68fa6c1d1e209131cea32507 |
| DINO | 82 | Not recorded | 68fa6c1d1e209131cea32507 |
| Barlow Twins | 81.5 | Not recorded | 68fa6c1d1e209131cea32507 |
| Supervised | 81.3 | Not recorded | 68fa6c1d1e209131cea32507 |

### CoKe

AP@50: 83.2. Result ID: 698ede13ffc3901de0a2707f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32507.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32507.md>)

[Implementation](<https://github.com/idstcv/CoKe>)

Recorded evaluation configuration: {"Backbone":"R50-C4","Evaluation Protocol":"fine-tuning","multi-crop training trick":false}. This record does not assert independent reproduction.

### MoCo-v2

AP@50: 83. Result ID: 698ede13ffc3901de0a2707a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32507.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa673f1e209131cea15344.md>)

[Implementation](<https://github.com/facebookresearch/moco>)

Recorded evaluation configuration: {"Backbone":"R50-C4","Evaluation Protocol":"fine-tuning","multi-crop training trick":false}. This record does not assert independent reproduction.

### BYOL

AP@50: 82.9. Result ID: 698ede13ffc3901de0a2707c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32507.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684a1e209131cea1b1e9.md>)

[Implementation](<https://github.com/deepmind/deepmind-research/tree/byol>)

Recorded evaluation configuration: {"Backbone":"R50-C4","Evaluation Protocol":"fine-tuning","multi-crop training trick":false}. This record does not assert independent reproduction.

### SwAV

AP@50: 82.1. Result ID: 698ede13ffc3901de0a2707d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32507.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690b1e209131cea1faec.md>)

[Implementation](<https://github.com/facebookresearch/swav>)

Recorded evaluation configuration: {"Backbone":"R50-C4","Evaluation Protocol":"fine-tuning","multi-crop training trick":true}. This record does not assert independent reproduction.

### DINO

AP@50: 82. Result ID: 698ede13ffc3901de0a2707e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32507.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea2594c.md>)

[Implementation](<https://github.com/facebookresearch/dino>)

Recorded evaluation configuration: {"Backbone":"R50-C4","Evaluation Protocol":"fine-tuning","multi-crop training trick":true}. This record does not assert independent reproduction.

### Barlow Twins

AP@50: 81.5. Result ID: 698ede13ffc3901de0a2707b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32507.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f141e209131ce9e75ab.md>)

[Implementation](<https://github.com/facebookresearch/barlowtwins>)

Recorded evaluation configuration: {"Backbone":"R50-C4","Evaluation Protocol":"fine-tuning","multi-crop training trick":false}. This record does not assert independent reproduction.

### Supervised

AP@50: 81.3. Result ID: 698ede13ffc3901de0a27079.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32507.md>)

Recorded evaluation configuration: {"Backbone":"R50-C4","Evaluation Protocol":"fine-tuning","multi-crop training trick":false}. This record does not assert independent reproduction.

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