# Multi-label Recognition on NUS-WIDE seen & unseen (P/R/F1@3/5, mAP)

Source: [Multi-label Recognition on NUS-WIDE seen & unseen (P/R/F1@3/5, mAP)](<https://www.sota2.com/research/sota/multi-label-recognition-on-nus-wide-seen-and-unseen-p-r-f1-at-3-5-map>)

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

Data updated: 2026-02-26T05:43:55.026Z

Evaluation of Multi-label Recognition performance on the NUS-WIDE dataset configuration involving both seen and unseen classes, reporting Precision, Recall, and F1 scores at K=3 and K=5, alongside mAP.

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 | Multi-label Recognition |
| Dataset (including any stated split) | NUS-WIDE seen & unseen |
| Metric | F1 Score @ 3 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [F1 Score @ 3](<https://www.sota2.com/research/sota/multi-label-recognition-on-nus-wide-seen-and-unseen-p-r-f1-at-3-5-map.md?metric=F1%20Score%20%40%203>): Higher is better; unit: PERCENT.

- [Precision @ 3](<https://www.sota2.com/research/sota/multi-label-recognition-on-nus-wide-seen-and-unseen-p-r-f1-at-3-5-map.md?metric=Precision%20%40%203>): Higher is better; unit: PERCENT.

- [Recall @ 3](<https://www.sota2.com/research/sota/multi-label-recognition-on-nus-wide-seen-and-unseen-p-r-f1-at-3-5-map.md?metric=Recall%20%40%203>): Higher is better; unit: PERCENT.

- [Precision @ 5](<https://www.sota2.com/research/sota/multi-label-recognition-on-nus-wide-seen-and-unseen-p-r-f1-at-3-5-map.md?metric=Precision%20%40%205>): Higher is better; unit: PERCENT.

- [Recall @ 5](<https://www.sota2.com/research/sota/multi-label-recognition-on-nus-wide-seen-and-unseen-p-r-f1-at-3-5-map.md?metric=Recall%20%40%205>): Higher is better; unit: PERCENT.

- [F1 Score @ 5](<https://www.sota2.com/research/sota/multi-label-recognition-on-nus-wide-seen-and-unseen-p-r-f1-at-3-5-map.md?metric=F1%20Score%20%40%205>): Higher is better; unit: PERCENT.

- [mAP (Mean Average Precision)](<https://www.sota2.com/research/sota/multi-label-recognition-on-nus-wide-seen-and-unseen-p-r-f1-at-3-5-map.md?metric=mAP%20(Mean%20Average%20Precision)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score @ 3 | Result date | Report paper |
| --- | --- | --- | --- |
| RAM | 23.5 | Not recorded | 68fa77861e209131cea73d08 |
| MKT | 22 | Not recorded | 68fa77861e209131cea73d08 |
| DualCoOp++ | 21.1 | Not recorded | 68fa77861e209131cea73d08 |
| TGF | 20.7 | Not recorded | 68fa77861e209131cea73d08 |
| DualCoOp | 19.4 | Not recorded | 68fa77861e209131cea73d08 |
| SDLM | 18.5 | Not recorded | 68fa77861e209131cea73d08 |
| OVML | 18.3 | Not recorded | 68fa77861e209131cea73d08 |
| CLIP | 16.5 | Not recorded | 68fa77861e209131cea73d08 |
| BIAM | 16.1 | Not recorded | 68fa77861e209131cea73d08 |
| LESAM | 14.4 | Not recorded | 68fa77861e209131cea73d08 |

### RAM

F1 Score @ 3: 23.5. Result ID: 69952c6d3badfaffe612ac4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77861e209131cea73d08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77861e209131cea73d08.md>)

[Implementation](<https://github.com/EricTan7/RAM>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### MKT

F1 Score @ 3: 22. Result ID: 69952c6d3badfaffe612ac49.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77861e209131cea73d08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e721e209131cea3fe06.md>)

[Implementation](<https://github.com/sunanhe/MKT>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### DualCoOp++

F1 Score @ 3: 21.1. Result ID: 69952c6d3badfaffe612ac47.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77861e209131cea73d08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71701e209131cea513ed.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### TGF

F1 Score @ 3: 20.7. Result ID: 69952c6d3badfaffe612ac4a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77861e209131cea73d08.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### DualCoOp

F1 Score @ 3: 19.4. Result ID: 69952c6d3badfaffe612ac46.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77861e209131cea73d08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cdb1e209131cea3653f.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### SDLM

F1 Score @ 3: 18.5. Result ID: 69952c6d3badfaffe612ac44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77861e209131cea73d08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69f11e209131cea251ff.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### OVML

F1 Score @ 3: 18.3. Result ID: 69952c6d3badfaffe612ac48.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77861e209131cea73d08.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### CLIP

F1 Score @ 3: 16.5. Result ID: 69952c6d3badfaffe612ac45.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77861e209131cea73d08.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### BIAM

F1 Score @ 3: 16.1. Result ID: 69952c6d3badfaffe612ac43.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77861e209131cea73d08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a971e209131cea292c9.md>)

[Implementation](<https://github.com/akshitac8/BiAM>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### LESAM

F1 Score @ 3: 14.4. Result ID: 69952c6d3badfaffe612ac42.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77861e209131cea73d08.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

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