Image Captioning on nocaps XD (val)
106.8CIDErLEMON_base
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LEMON_basePre-training data=ALT200M [31]2022.09 | 106.8 | 14.1 | |
| P2CPre-training data=CC3M2022.09 | 104.1 | 14.6 | |
| LEMON_basePre-training data=CC12M2022.09 | 100.4 | 13.8 | |
| P2CPre-training data=COCO Caption 0.5M2022.09 | 97.2 | 14.2 | |
| VinVL_basePre-training data=5.65M Combined2022.09 | 95.5 | 13.5 | |
| LEMON_basePre-training data=CC3M [38]2022.09 | 91.6 | 13 | |
| Encoder-DecoderPre-training data=CC3M+CC12M2022.09 | 90.2 | 12.1 | |
| Encoder-DecoderPre-training data=CC12M [43]2022.09 | 87.4 | 11.8 |