Image Captioning on VizWiz (test)
125.7CIDErPaLI-X (Specialist)
Evaluation Results
| Method | Links | |
|---|---|---|
| PaLI-X (Specialist)OCR pipeline input=true, Model Category=Specialist, Reference Citation=[7]2023.12 | 125.7 | |
| SMoLA-PaLI-XFTOCR pipeline input=true, Model Category=Generalist, Backbone=PaLI-X2023.12 | 124.6 | |
| PaLI-X (Specialist)OCR pipeline input=false, Model Category=Specialist, Reference Citation=[7]2023.12 | 122.7 | |
| SOTAEvaluation Protocol=Pre-training & finetuning2022.09 | 120.8 | |
| SMoLA-PaLI-3FTOCR pipeline input=true, Model Category=Generalist, Backbone=PaLI-32023.12 | 120.4 | |
| SMoLA-PaLI-XFTOCR pipeline input=false, Model Category=Generalist, Backbone=PaLI-X2023.12 | 120.3 | |
| SMoLA-PaLI-3FTOCR pipeline input=false, Model Category=Generalist, Backbone=PaLI-32023.12 | 119.8 | |
| SMALLCAPEvaluation Protocol=Zero-shot (trained on COCO), Datastore=In-domain + Web2022.09 | 55 | |
| CaMELEvaluation Protocol=Zero-shot (trained on COCO)2022.09 | 37.6 | |
| ClipCapEvaluation Protocol=Zero-shot (trained on COCO)2022.09 | 28.3 |