# Object Detection on Clipart1k (unseen target domain)

Source: [Object Detection on Clipart1k (unseen target domain)](<https://www.sota2.com/research/sota/object-detection-on-clipart1k-unseen-target-domain>)

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

Data updated: 2026-02-27T07:16:29.782Z

Evaluation of Object Detection performance on the Clipart1k dataset, specifically focusing on results derived from an unseen target domain. Metrics include class-specific scores (bicycle, bird, car, cat, dog, person) and overall mAP.

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) | Clipart1k (unseen target domain) |
| Metric | Bicycle AP |
| 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

- [Bicycle AP](<https://www.sota2.com/research/sota/object-detection-on-clipart1k-unseen-target-domain.md?metric=Bicycle%20AP>): Higher is better; unit: PERCENT.

- [Bird AP](<https://www.sota2.com/research/sota/object-detection-on-clipart1k-unseen-target-domain.md?metric=Bird%20AP>): Higher is better; unit: PERCENT.

- [Car AP](<https://www.sota2.com/research/sota/object-detection-on-clipart1k-unseen-target-domain.md?metric=Car%20AP>): Higher is better; unit: PERCENT.

- [Cat AP](<https://www.sota2.com/research/sota/object-detection-on-clipart1k-unseen-target-domain.md?metric=Cat%20AP>): Higher is better; unit: PERCENT.

- [Dog AP](<https://www.sota2.com/research/sota/object-detection-on-clipart1k-unseen-target-domain.md?metric=Dog%20AP>): Higher is better; unit: PERCENT.

- [Person AP](<https://www.sota2.com/research/sota/object-detection-on-clipart1k-unseen-target-domain.md?metric=Person%20AP>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/object-detection-on-clipart1k-unseen-target-domain.md?metric=mAP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Bicycle AP | Result date | Report paper |
| --- | --- | --- | --- |
| AT | 78.6 | Not recorded | 68fa6c891e209131cea34913 |
| MT + Ldis | 73.2 | Not recorded | 68fa6c891e209131cea34913 |
| MT + WS Aug. | 68.2 | Not recorded | 68fa6c891e209131cea34913 |
| MT | 64.8 | Not recorded | 68fa6c891e209131cea34913 |
| Oracle | 47.6 | Not recorded | 68fa6c891e209131cea34913 |

### AT

Bicycle AP: 78.6. Result ID: 69a144cc35dfcabb00e5e91d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c891e209131cea34913.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c891e209131cea34913.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-101","Source Domains":"PASCAL VOC (sup.) & Watercolor2k (unsup.)"}. This record does not assert independent reproduction.

### MT + Ldis

Bicycle AP: 73.2. Result ID: 69a144cc35dfcabb00e5e91f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c891e209131cea34913.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03b45.md>)

[Implementation](<https://github.com/CuriousAI/mean-teacher>)

Recorded evaluation configuration: {"Backbone":"ResNet-101","Source Domains":"PASCAL VOC (sup.) & Watercolor2k (unsup.)"}. This record does not assert independent reproduction.

### MT + WS Aug.

Bicycle AP: 68.2. Result ID: 69a144cc35dfcabb00e5e91e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c891e209131cea34913.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03b45.md>)

[Implementation](<https://github.com/CuriousAI/mean-teacher>)

Recorded evaluation configuration: {"Backbone":"ResNet-101","Source Domains":"PASCAL VOC (sup.) & Watercolor2k (unsup.)"}. This record does not assert independent reproduction.

### MT

Bicycle AP: 64.8. Result ID: 69a144cc35dfcabb00e5e920.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c891e209131cea34913.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03b45.md>)

[Implementation](<https://github.com/CuriousAI/mean-teacher>)

Recorded evaluation configuration: {"Backbone":"ResNet-101","Source Domains":"PASCAL VOC (sup.) & Watercolor2k (unsup.)"}. This record does not assert independent reproduction.

### Oracle

Bicycle AP: 47.6. Result ID: 69a144cc35dfcabb00e5e921.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c891e209131cea34913.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-101","Note":"Fully supervised"}. This record does not assert independent reproduction.

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