Research
Benchmarks for “coco”
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
3,140 benchmarksPage 85 of 126
Search results
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Localization | RefCOCOg (test) | 6 | Feb 26, 2026 | ||
| Localization | RefCOCO+ (test) | 6 | Feb 26, 2026 | ||
| Localization | RefCOCO (test) | 6 | Feb 26, 2026 | ||
| Object Removal | COCO-10K | 6 | Feb 26, 2026 | ||
| Referring Image Segmentation | refCOCO+ UMD (val) | 6 | Feb 26, 2026 | ||
| Referring Image Segmentation | refCOCO UMD (val) | 6 | Feb 26, 2026 | ||
| Backdoor Detoxification | MS-COCO Average across attacks | 6 | Feb 26, 2026 | ||
| Backdoor Detoxification | MS-COCO PersonalBKD_dream | 6 | Feb 26, 2026 | ||
| Backdoor Detoxification | MS-COCO EvilEdit | 6 | Feb 26, 2026 | ||
| Backdoor Detoxification | MS-COCO BadT2I_sent | 6 | Feb 26, 2026 | ||
| Backdoor Detoxification | MS-COCO BadT2I_tok | 6 | Feb 26, 2026 | ||
| Semantic Segmentation | COCO-Stuff (C-Stf) | 6 | Feb 26, 2026 | ||
| Semantic Segmentation | COCO-Object | 6 | Feb 26, 2026 | ||
| Open-vocabulary semantic segmentation | COCONutL | 6 | Feb 26, 2026 | ||
| Image Retrieval | MS-COCO zero-shot | 6 | Feb 26, 2026 | ||
| Text Retrieval | MS-COCO zero-shot | 6 | Feb 26, 2026 | ||
| Multi-label Recognition | MS-COCO (seen and unseen) | 6 | Feb 26, 2026 | ||
| Multi-label Recognition | MS-COCO (unseen) | 6 | Feb 26, 2026 | ||
| Image Generation | MS-COCO 5,000 samples 2017 (val) | 6 | Feb 26, 2026 | ||
| Text-to-Image Generation (Prior Preservation) | MS COCO 30k (val) | 6 | Feb 26, 2026 | ||
| Layout-to-Image Generation | RC COCO | 6 | Feb 26, 2026 | ||
| Referring Expression Segmentation | gRefCOCO | 6 | Feb 26, 2026 | ||
| Referring Description | RefCOCOg | 6 | Feb 26, 2026 | ||
| Image Reconstruction | MSCOCO 64x64 (test) | 6 | Feb 26, 2026 | ||
| Amodal Segmentation | COCO-A (test) | 6 | Feb 26, 2026 |