# Instance Retrieval on UCS corpus (unseen sound events)

Source: [Instance Retrieval on UCS corpus (unseen sound events)](<https://www.sota2.com/research/sota/instance-retrieval-on-ucs-corpus-unseen-sound-events>)

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

Data updated: 2026-07-07T06:42:56.057Z

Evaluation of Instance Retrieval performance on the UCS corpus, focusing on unseen sound events, measured using R@1.

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 | Instance Retrieval |
| Dataset (including any stated split) | UCS corpus (unseen sound events) |
| Metric | R@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [R@1](<https://www.sota2.com/research/sota/instance-retrieval-on-ucs-corpus-unseen-sound-events.md?metric=R%401>): Higher is better; unit: PERCENT.

## Recorded results

| Method | R@1 | Result date | Report paper |
| --- | --- | --- | --- |
| M2D | 98.8 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| BEATs | 96.6 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| AudioMAE | 96.6 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| AST | 94 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| M2D | 89.5 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| BEATs | 82.6 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| AST | 81.5 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| AudioMAE | 80.4 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| CLAP | 80 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| PANNs CNN14 | 73.1 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| PANNs CNN14 | 65.7 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| CLAP | 61.1 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| M2D | 48.6 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| AudioMAE | 45.2 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| BEATs | 33.5 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| PANNs CNN14 | 31.6 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| AST | 29.5 | Not recorded | 6a4c882e85dba69fef8b2b66 |
| CLAP | 26.9 | Not recorded | 6a4c882e85dba69fef8b2b66 |

### M2D

R@1: 98.8. Result ID: 6a4c9fef60b88bb339c6dc65.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"instance head","pretraining":"self-supervised (AS2M)"}. This record does not assert independent reproduction.

### BEATs

R@1: 96.6. Result ID: 6a4c9fef60b88bb339c6dc62.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"instance head","pretraining":"self-supervised (AS2M)"}. This record does not assert independent reproduction.

### AudioMAE

R@1: 96.6. Result ID: 6a4c9fef60b88bb339c6dc68.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"instance head","pretraining":"self-supervised (AS2M)"}. This record does not assert independent reproduction.

### AST

R@1: 94. Result ID: 6a4c9fef60b88bb339c6dc5f.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"instance head","pretraining":"supervised (AudioSet)"}. This record does not assert independent reproduction.

### M2D

R@1: 89.5. Result ID: 6a4c9fef60b88bb339c6dc63.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"frozen","pretraining":"self-supervised (AS2M)"}. This record does not assert independent reproduction.

### BEATs

R@1: 82.6. Result ID: 6a4c9fef60b88bb339c6dc60.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"frozen","pretraining":"self-supervised (AS2M)"}. This record does not assert independent reproduction.

### AST

R@1: 81.5. Result ID: 6a4c9fef60b88bb339c6dc5d.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"frozen","pretraining":"supervised (AudioSet)"}. This record does not assert independent reproduction.

### AudioMAE

R@1: 80.4. Result ID: 6a4c9fef60b88bb339c6dc66.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"frozen","pretraining":"self-supervised (AS2M)"}. This record does not assert independent reproduction.

### CLAP

R@1: 80. Result ID: 6a4c9fef60b88bb339c6dc59.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"instance head","pretraining":"audio-text contrastive"}. This record does not assert independent reproduction.

### PANNs CNN14

R@1: 73.1. Result ID: 6a4c9fef60b88bb339c6dc5c.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"instance head","pretraining":"supervised (AudioSet)"}. This record does not assert independent reproduction.

### PANNs CNN14

R@1: 65.7. Result ID: 6a4c9fef60b88bb339c6dc5a.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"frozen","pretraining":"supervised (AudioSet)"}. This record does not assert independent reproduction.

### CLAP

R@1: 61.1. Result ID: 6a4c9fef60b88bb339c6dc57.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"frozen","pretraining":"audio-text contrastive"}. This record does not assert independent reproduction.

### M2D

R@1: 48.6. Result ID: 6a4c9fef60b88bb339c6dc64.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"class head","pretraining":"self-supervised (AS2M)"}. This record does not assert independent reproduction.

### AudioMAE

R@1: 45.2. Result ID: 6a4c9fef60b88bb339c6dc67.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"class head","pretraining":"self-supervised (AS2M)"}. This record does not assert independent reproduction.

### BEATs

R@1: 33.5. Result ID: 6a4c9fef60b88bb339c6dc61.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"class head","pretraining":"self-supervised (AS2M)"}. This record does not assert independent reproduction.

### PANNs CNN14

R@1: 31.6. Result ID: 6a4c9fef60b88bb339c6dc5b.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"class head","pretraining":"supervised (AudioSet)"}. This record does not assert independent reproduction.

### AST

R@1: 29.5. Result ID: 6a4c9fef60b88bb339c6dc5e.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"class head","pretraining":"supervised (AudioSet)"}. This record does not assert independent reproduction.

### CLAP

R@1: 26.9. Result ID: 6a4c9fef60b88bb339c6dc58.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b66.md>)

Recorded evaluation configuration: {"evaluation\_protocol":"class head","pretraining":"audio-text contrastive"}. This record does not assert independent reproduction.

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