# Place Recognition on U.S. (University Sector) in-house (test)

Source: [Place Recognition on U.S. (University Sector) in-house (test)](<https://www.sota2.com/research/sota/place-recognition-on-u-s-university-sector-in-house-test>)

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

Data updated: 2026-02-26T05:36:19.949Z

Evaluation of Place Recognition performance on the test split of the proprietary U.S. University Sector in-house dataset, measured using recall metrics.

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 | Place Recognition |
| Dataset (including any stated split) | U.S. (University Sector) in-house (test) |
| Metric | Avg Recall @ 1% |
| 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

- [Avg Recall @ 1%](<https://www.sota2.com/research/sota/place-recognition-on-u-s-university-sector-in-house-test.md?metric=Avg%20Recall%20%40%201%25>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Avg Recall @ 1% | Result date | Report paper |
| --- | --- | --- | --- |
| LPD-Net | 96 | Not recorded | 68fa6a071e209131cea25914 |
| SOE-Net | 93.17 | Not recorded | 68fa6a071e209131cea25914 |
| DAGC | 83.49 | Not recorded | 68fa6a071e209131cea25914 |
| PCAN | 79.05 | Not recorded | 68fa6a071e209131cea25914 |
| PointNetVLAD | 72.63 | Not recorded | 68fa6a071e209131cea25914 |

### LPD-Net

Avg Recall @ 1%: 96. Result ID: 698e006dffc3901de09a0dc3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea25914.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66341e209131cea0ebc4.md>)

Recorded evaluation configuration: {"Descriptor Dimension":"256-dim","Training Data":"Oxford RobotCar"}. This record does not assert independent reproduction.

### SOE-Net

Avg Recall @ 1%: 93.17. Result ID: 698e006dffc3901de09a0dc1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea25914.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea25914.md>)

[Implementation](<https://github.com/Yan-Xia/SOE-Net>)

Recorded evaluation configuration: {"Descriptor Dimension":"256-dim","Training Data":"Oxford RobotCar"}. This record does not assert independent reproduction.

### DAGC

Avg Recall @ 1%: 83.49. Result ID: 698e006dffc3901de09a0dc2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea25914.md>)

Recorded evaluation configuration: {"Descriptor Dimension":"256-dim","Training Data":"Oxford RobotCar"}. This record does not assert independent reproduction.

### PCAN

Avg Recall @ 1%: 79.05. Result ID: 698e006dffc3901de09a0dc4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea25914.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a91e209131cea0bb54.md>)

Recorded evaluation configuration: {"Descriptor Dimension":"256-dim","Training Data":"Oxford RobotCar"}. This record does not assert independent reproduction.

### PointNetVLAD

Avg Recall @ 1%: 72.63. Result ID: 698e006dffc3901de09a0dc5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea25914.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64641e209131cea04561.md>)

[Implementation](<https://github.com/mikacuy/pointnetvlad.git>)

Recorded evaluation configuration: {"Descriptor Dimension":"256-dim","Training Data":"Oxford RobotCar"}. This record does not assert independent reproduction.

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