Image Captioning on MS-COCO Karpathy 2014 (test)
41.3BLEU-4GIT
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| GITPretrain Data=4M2023.05 | 41.3 | 139.1 | — | 30.4 | — | 24.3 | |
| ViTCapPretrain Data=4M2023.05 | 41.2 | 138.1 | — | 30.1 | — | 24.1 | |
| HAAVPretrain Data=None2023.05 | 41 | 141.5 | — | 30.2 | — | 23.9 | |
| VinVLPretrain Data=8.8M2023.05 | 40.9 | 140.4 | — | 30.9 | — | 25.1 | |
| OscarPretrain Data=6.5M2023.05 | 40.5 | 137.6 | — | 29.7 | — | 22.8 | |
| X-VLMPretrain Data=16M2023.05 | 40.4 | 139.3 | — | — | — | — | |
| CLIP-ViLPretrain Data=None2023.05 | 40.2 | 134.2 | — | 29.7 | — | 23.8 | |
| DLCTPretrain Data=None2023.05 | 39.8 | 133.8 | — | 29.5 | — | 23 | |
| Xmodal-CtxPretrain Data=None2023.05 | 39.7 | 135.9 | — | 30 | — | 23.7 | |
| VLPPretrain Data=3M2023.05 | 39.5 | 129.3 | — | 29.3 | — | 23.2 | |
| X-LANPretrain Data=None2023.05 | 39.5 | 132 | — | 29.5 | — | 23.4 | |
| M²Pretrain Data=None2023.05 | 39.1 | 131.2 | — | 29.1 | — | 22.6 | |
| SimVLMbasePretrain Data=1.8B2023.05 | 39 | 134.8 | — | 32.9 | — | 24 | |
| AoANetPretrain Data=None2023.05 | 38.9 | 129.8 | — | 29.2 | — | 22.4 | |
| Up-DownPretrain Data=None2023.05 | 36.3 | 120.1 | — | 27.7 | — | 21.4 | |
| SCSTPretrain Data=None2023.05 | 34.2 | 114 | — | 26.7 | — | — | |
| 3 LBL ensembleOptimization method=DNGO, Ensemble Size=32015.02 | 26.7 | — | — | — | — | — | |
| 2 LBL ensembleOptimization method=DNGO, Ensemble Size=22015.02 | 25.9 | — | — | — | — | — | |
| Single LBLOptimization method=DNGO, Ensemble Size=12015.02 | 25.1 | — | — | — | — | — | |
| Hard-Attention LSTM2015.02 | 25 | — | — | — | — | — | |
| 10 LSTM ensembleEnsemble Size=102015.02 | 24.4 | — | — | — | — | — | |
| Human Expert LBLHyperparameter Tuning=Human Expert2015.02 | 24.3 | — | — | — | — | — | |
| Regularized LSTM2015.02 | 24.3 | — | — | — | — | — | |
| Soft-Attention LSTM2015.02 | 24.3 | — | — | — | — | — | |
| AnyGPTParameters=8B, zero-shot=true2024.02 | — | 107.5 | — | — | — | — | |
| DreamLLMParameters=8B, zero-shot=true2024.02 | — | 115.4 | — | — | — | — | |
| EmuParameters=14B, zero-shot=true2024.02 | — | 112.4 | — | — | — | — | |
| FlamingoParameters=9B, zero-shot=true2024.02 | — | 79.4 | — | — | — | — | |
| FlamingoParameters=80B, zero-shot=true2024.02 | — | 84.3 | — | — | — | — | |
| InstructBLIPParameters=14B, zero-shot=false, trained on training samples=true2024.02 | — | 102.2 | — | — | — | — | |
| SEED-LLaMAParameters=8B, zero-shot=false, trained on training samples=true2024.02 | — | 123.6 | — | — | — | — |