# Multi-label Recognition on MS-COCO 2014 (val) Source: [Multi-label Recognition on MS-COCO 2014 (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:09:58.914Z Evaluation of Multi-label Recognition performance on the validation split of the MS-COCO 2014 dataset, reporting Mean Average Precision (mAP) across various Intersection over Union (IoU) thresholds (10% to 90%). 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) | MS-COCO 2014 (val) | | Metric | mAP@0.10 | | 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 - [mAP@0.10](): Higher is better; unit: PERCENT. - [mAP@0.20](): Higher is better; unit: PERCENT. - [mAP@0.30](): Higher is better; unit: PERCENT. - [mAP@0.40](): Higher is better; unit: PERCENT. - [mAP@0.50](): Higher is better; unit: PERCENT. - [mAP@0.60](): Higher is better; unit: PERCENT. - [mAP@0.70](): Higher is better; unit: PERCENT. - [mAP@0.80](): Higher is better; unit: PERCENT. - [mAP@0.90](): Higher is better; unit: PERCENT. - [mAP (Avg)](): Higher is better; unit: PERCENT. ## Recorded results | Method | mAP@0.10 | Result date | Report paper | | --- | --- | --- | --- | | DualCoop | 78.7 | Not recorded | 68fa6cdb1e209131cea3653f | | SARB\* | 75.5 | Not recorded | 68fa6cdb1e209131cea3653f | | SARB | 71.2 | Not recorded | 68fa6cdb1e209131cea3653f | | SST\* | 69.1 | Not recorded | 68fa6cdb1e209131cea3653f | | SST | 68.1 | Not recorded | 68fa6cdb1e209131cea3653f | | KGGR | 66.6 | Not recorded | 68fa6cdb1e209131cea3653f | | GCN-ML | 63.8 | Not recorded | 68fa6cdb1e209131cea3653f | | SSGRL | 62.5 | Not recorded | 68fa6cdb1e209131cea3653f | | Partial BCE | 61.6 | Not recorded | 68fa6cdb1e209131cea3653f | | Curriculum labeling | 26.7 | Not recorded | 68fa6cdb1e209131cea3653f | ### DualCoop mAP@0.10: 78.7. Result ID: 698f46a23a6c314849f7a080. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#P":"1.3M"}. This record does not assert independent reproduction. ### SARB\* mAP@0.10: 75.5. Result ID: 698f46a23a6c314849f7a07f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#P":"29.6M","Pretraining":"CLIP weights \[46\]"}. This record does not assert independent reproduction. ### SARB mAP@0.10: 71.2. Result ID: 698f46a23a6c314849f7a07e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#P":"29.6M"}. This record does not assert independent reproduction. ### SST\* mAP@0.10: 69.1. Result ID: 698f46a23a6c314849f7a07d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#P":"33.5M","Pretraining":"CLIP weights \[46\]"}. This record does not assert independent reproduction. ### SST mAP@0.10: 68.1. Result ID: 698f46a23a6c314849f7a07c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#P":"33.5M"}. This record does not assert independent reproduction. ### KGGR mAP@0.10: 66.6. Result ID: 698f46a23a6c314849f7a079. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#P":"\> 25M"}. This record does not assert independent reproduction. ### GCN-ML mAP@0.10: 63.8. Result ID: 698f46a23a6c314849f7a078. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#P":"44.9M"}. This record does not assert independent reproduction. ### SSGRL mAP@0.10: 62.5. Result ID: 698f46a23a6c314849f7a077. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#P":"64.7M"}. This record does not assert independent reproduction. ### Partial BCE mAP@0.10: 61.6. Result ID: 698f46a23a6c314849f7a07b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#P":"\> 38M"}. This record does not assert independent reproduction. ### Curriculum labeling mAP@0.10: 26.7. Result ID: 698f46a23a6c314849f7a07a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#P":"≥ 38M"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.