# Shadow Detection Resource Usage on SBU

Source: [Shadow Detection Resource Usage on SBU](<https://www.sota2.com/research/sota/shadow-detection-resource-usage-on-sbu>)

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

Data updated: 2026-02-26T06:06:20.399Z

Evaluation focusing on the computational time required for training and testing models for Shadow Detection on the SBU dataset.

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 | Shadow Detection |
| Dataset (including any stated split) | SBU |
| Metric | Testing Time (hours) |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [Testing Time (hours)](<https://www.sota2.com/research/sota/shadow-detection-resource-usage-on-sbu.md?metric=Testing%20Time%20(hours)>): Lower is better; unit: TIME.

- [Testing Latency (sec/image)](<https://www.sota2.com/research/sota/shadow-detection-resource-usage-on-sbu.md?metric=Testing%20Latency%20(sec%2Fimage)>): Lower is better; unit: TIME.

- [Training Time (hours)](<https://www.sota2.com/research/sota/shadow-detection-resource-usage-on-sbu.md?metric=Training%20Time%20(hours)>): Lower is better; unit: TIME.

## Recorded results

| Method | Testing Time (hours) | Result date | Report paper |
| --- | --- | --- | --- |
| Our method | 0.33 | Not recorded | 68fa64251e209131cea02d59 |
| Unary-Pairwise | 9.13 | Not recorded | 68fa64251e209131cea02d59 |
| Stacked-CNN | 25.08 | Not recorded | 68fa64251e209131cea02d59 |

### Our method

Testing Time (hours): 0.33. Result ID: 698c0cbef729bc7f68e80554.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64251e209131cea02d59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64251e209131cea02d59.md>)

Recorded evaluation configuration: {"Hardware":"GPU"}. This record does not assert independent reproduction.

### Unary-Pairwise

Testing Time (hours): 9.13. Result ID: 698c0cbef729bc7f68e80553.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64251e209131cea02d59.md>)

Recorded evaluation configuration: {"Hardware":"GPU"}. This record does not assert independent reproduction.

### Stacked-CNN

Testing Time (hours): 25.08. Result ID: 698c0cbef729bc7f68e80552.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64251e209131cea02d59.md>)

Recorded evaluation configuration: {"Hardware":"GPU"}. This record does not assert independent reproduction.

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