# Contour and Boundary Detection on NYUD (test)

Source: [Contour and Boundary Detection on NYUD (test)](<https://www.sota2.com/research/sota/contour-and-boundary-detection-on-nyud-test>)

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

Data updated: 2026-02-26T05:54:04.062Z

Evaluation of Contour and Boundary Detection performance on the test split of the NYUD dataset, reporting ODS, OIS, and AP 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 | Contour and Boundary Detection |
| Dataset (including any stated split) | NYUD (test) |
| Metric | ODS |
| 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

- [ODS](<https://www.sota2.com/research/sota/contour-and-boundary-detection-on-nyud-test.md?metric=ODS>): Higher is better; unit: PERCENT.

- [OIS](<https://www.sota2.com/research/sota/contour-and-boundary-detection-on-nyud-test.md?metric=OIS>): Higher is better; unit: PERCENT.

- [AP](<https://www.sota2.com/research/sota/contour-and-boundary-detection-on-nyud-test.md?metric=AP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ODS | Result date | Report paper |
| --- | --- | --- | --- |
| RCF | 74.3 | Not recorded | 68fa66fc1e209131cea13757 |
| HED | 72 | Not recorded | 68fa66fc1e209131cea13757 |
| DexiNed-f | 65.8 | Not recorded | 68fa66fc1e209131cea13757 |
| gPb | 63.2 | Not recorded | 68fa66fc1e209131cea13757 |
| DexiNed-a | 60.2 | Not recorded | 68fa66fc1e209131cea13757 |

### RCF

ODS: 74.3. Result ID: 698d12ae8b517eb4331ecce4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66fc1e209131cea13757.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fc1e209131cea0db7f.md>)

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

### HED

ODS: 72. Result ID: 698d12ae8b517eb4331ecce3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66fc1e209131cea13757.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62161e209131ce9f7746.md>)

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

### DexiNed-f

ODS: 65.8. Result ID: 698d12ae8b517eb4331ecce5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66fc1e209131cea13757.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66fc1e209131cea13757.md>)

[Implementation](<https://github.com/xavysp/DexiNed>)

Recorded evaluation configuration: {"prediction\_type":"fused"}. This record does not assert independent reproduction.

### gPb

ODS: 63.2. Result ID: 698d12ae8b517eb4331ecce2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66fc1e209131cea13757.md>)

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

### DexiNed-a

ODS: 60.2. Result ID: 698d12ae8b517eb4331ecce6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66fc1e209131cea13757.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66fc1e209131cea13757.md>)

[Implementation](<https://github.com/xavysp/DexiNed>)

Recorded evaluation configuration: {"prediction\_type":"averaged"}. This record does not assert independent reproduction.

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