# Visual Place Recognition on Baidu Mall (test)

Source: [Visual Place Recognition on Baidu Mall (test)](<https://www.sota2.com/research/sota/visual-place-recognition-on-baidu-mall-test>)

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

Data updated: 2026-02-27T09:28:23.674Z

Evaluation of Visual Place Recognition performance on the test split of the Baidu Mall dataset, measured using Recall@1 and Recall@5.

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 | Visual Place Recognition |
| Dataset (including any stated split) | Baidu Mall (test) |
| Metric | Recall@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Recall@1](<https://www.sota2.com/research/sota/visual-place-recognition-on-baidu-mall-test.md?metric=Recall%401>): Higher is better; unit: PERCENT.

- [Recall@5](<https://www.sota2.com/research/sota/visual-place-recognition-on-baidu-mall-test.md?metric=Recall%405>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Recall@1 | Result date | Report paper |
| --- | --- | --- | --- |
| SegVLAD-PreT | 80.4 | Not recorded | 68fa74f31e209131cea64c1d |
| SegVLAD-PreT | 78.5 | Not recorded | 68fa74f31e209131cea64c1d |
| AnyLoc | 75.2 | Not recorded | 68fa74f31e209131cea64c1d |
| SALAD | 74.8 | Not recorded | 68fa74f31e209131cea64c1d |
| SegVLAD-FineT | 69.9 | Not recorded | 68fa74f31e209131cea64c1d |
| SegVLAD-FineT | 69.7 | Not recorded | 68fa74f31e209131cea64c1d |
| MixVPR | 64.4 | Not recorded | 68fa74f31e209131cea64c1d |
| EigenPlaces | 56.5 | Not recorded | 68fa74f31e209131cea64c1d |
| CosPlace | 41.6 | Not recorded | 68fa74f31e209131cea64c1d |

### SegVLAD-PreT

Recall@1: 80.4. Result ID: 69a163ac35dfcabb00e6bd2e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Implementation](<https://github.com/AnyLoc/Revisit-Anything>)

Recorded evaluation configuration: {"Backbone Training":"PreT","Model Variant":"M"}. This record does not assert independent reproduction.

### SegVLAD-PreT

Recall@1: 78.5. Result ID: 69a163ac35dfcabb00e6bd2d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Implementation](<https://github.com/AnyLoc/Revisit-Anything>)

Recorded evaluation configuration: {"Backbone Training":"PreT","Model Variant":"D"}. This record does not assert independent reproduction.

### AnyLoc

Recall@1: 75.2. Result ID: 69a163ac35dfcabb00e6bd2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71471e209131cea50577.md>)

[Implementation](<https://anyloc.github.io/>)

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

### SALAD

Recall@1: 74.8. Result ID: 69a163ac35dfcabb00e6bd2c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73d51e209131cea5e630.md>)

[Implementation](<https://github.com/serizba/salad>)

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

### SegVLAD-FineT

Recall@1: 69.9. Result ID: 69a163ac35dfcabb00e6bd2f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Implementation](<https://github.com/AnyLoc/Revisit-Anything>)

Recorded evaluation configuration: {"Backbone Training":"FineT","Model Variant":"D"}. This record does not assert independent reproduction.

### SegVLAD-FineT

Recall@1: 69.7. Result ID: 69a163ac35dfcabb00e6bd30.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Implementation](<https://github.com/AnyLoc/Revisit-Anything>)

Recorded evaluation configuration: {"Backbone Training":"FineT","Model Variant":"M"}. This record does not assert independent reproduction.

### MixVPR

Recall@1: 64.4. Result ID: 69a163ac35dfcabb00e6bd29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb41e209131cea419f9.md>)

[Implementation](<https://github.com/amaralibey/MixVPR>)

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

### EigenPlaces

Recall@1: 56.5. Result ID: 69a163ac35dfcabb00e6bd2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70621e209131cea4ac7f.md>)

[Implementation](<https://github.com/gmberton/EigenPlaces>)

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

### CosPlace

Recall@1: 41.6. Result ID: 69a163ac35dfcabb00e6bd28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c1d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2e1e209131cea329cd.md>)

[Implementation](<https://github.com/gmberton/CosPlace>)

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

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