# Cross-modal Retrieval (Text to Image) on iNaturalist Species-level Retrieval seen

Source: [Cross-modal Retrieval (Text to Image) on iNaturalist Species-level Retrieval seen](<https://www.sota2.com/research/sota/cross-modal-retrieval-text-to-image-on-inaturalist-species-level-retrieval-seen>)

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

Data updated: 2026-03-26T13:47:31.380Z

Evaluation of Cross-modal Retrieval performance, specifically retrieving images from text queries, using the 'seen' split of the iNaturalist Species-level Retrieval dataset, measured using Top-K accuracy (Top 1 and Top 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 | Cross-modal Retrieval (Text to Image) |
| Dataset (including any stated split) | iNaturalist Species-level Retrieval seen |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/cross-modal-retrieval-text-to-image-on-inaturalist-species-level-retrieval-seen.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

- [Top-5 Accuracy](<https://www.sota2.com/research/sota/cross-modal-retrieval-text-to-image-on-inaturalist-species-level-retrieval-seen.md?metric=Top-5%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| BioVITA | 91.2 | Not recorded | 69c4bd7d0636e5bf4afc7573 |
| BioCLIP 2 | 84.8 | Not recorded | 69c4bd7d0636e5bf4afc7573 |
| BioVITA | 84.8 | Not recorded | 69c4bd7d0636e5bf4afc7573 |
| ImageBind | 67.9 | Not recorded | 69c4bd7d0636e5bf4afc7573 |
| TaxaBind | 66.9 | Not recorded | 69c4bd7d0636e5bf4afc7573 |
| CLIP | 63.8 | Not recorded | 69c4bd7d0636e5bf4afc7573 |
| Random | 0.01 | Not recorded | 69c4bd7d0636e5bf4afc7573 |

### BioVITA

Top-1 Accuracy: 91.2. Result ID: 69c538db47f34ce924aee34b.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd7d0636e5bf4afc7573.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bd7d0636e5bf4afc7573.md>)

Recorded evaluation configuration: {"Training Stage":"Stage2"}. This record does not assert independent reproduction.

### BioCLIP 2

Top-1 Accuracy: 84.8. Result ID: 69c538db47f34ce924aee348.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd7d0636e5bf4afc7573.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78e61e209131cea7b125.md>)

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

### BioVITA

Top-1 Accuracy: 84.8. Result ID: 69c538db47f34ce924aee34a.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd7d0636e5bf4afc7573.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bd7d0636e5bf4afc7573.md>)

Recorded evaluation configuration: {"Training Stage":"Stage1"}. This record does not assert independent reproduction.

### ImageBind

Top-1 Accuracy: 67.9. Result ID: 69c538db47f34ce924aee347.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd7d0636e5bf4afc7573.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f971e209131cea467c4.md>)

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

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

### TaxaBind

Top-1 Accuracy: 66.9. Result ID: 69c538db47f34ce924aee349.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd7d0636e5bf4afc7573.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa758d1e209131cea6891f.md>)

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

### CLIP

Top-1 Accuracy: 63.8. Result ID: 69c538db47f34ce924aee346.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd7d0636e5bf4afc7573.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

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

### Random

Top-1 Accuracy: 0.01. Result ID: 69c538db47f34ce924aee345.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd7d0636e5bf4afc7573.md>)

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.
