Image Captioning on cIC
77.6RegionScoreRavenea-CLIP
Evaluation results
| Method | Links | |
|---|---|---|
| Ravenea-CLIPRetriever State=Finetuned, VLM Backbone=Qwen2.5-VL-72B2025.05 | 77.6 | |
| Ravenea-CLIPRetriever State=Finetuned, VLM Backbone=InternVL3-78B2025.05 | 73.5 | |
| Ravenea-SigLIPRetriever State=Finetuned, VLM Backbone=InternVL3-78B2025.05 | 69.4 | |
| Ravenea-CLIPRetriever State=Finetuned, VLM Backbone=GPT-4.12025.05 | 69.4 | |
| VisualBERTRetriever State=Finetuned, VLM Backbone=GPT-4.12025.05 | 65.3 | |
| VL-T5Retriever State=Finetuned, VLM Backbone=GPT-4.12025.05 | 63.3 | |
| Ravenea-CLIPRetriever State=Finetuned, VLM Backbone=Qwen2.5-VL-7B2025.05 | 61.2 | |
| LLaVA-OV-7BRetriever State=Finetuned, VLM Backbone=GPT-4.12025.05 | 61.2 |