Image Captioning on Conceptual Captions

Metric: ROUGE-L (higher is better)

LeaderboardDataset
Loading chart...
#ModelROUGE-LExtra DataPaperDateCode
1ClipCap (MLP + GPT2 tuning)26.71NoClipCap: CLIP Prefix for Image Captioning2021-11-18Code
2ClipCap (Transformer)25.12NoClipCap: CLIP Prefix for Image Captioning2021-11-18Code