Object Counting On Tallyqa Simple
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| SMoLA-PaLI-X Generalist (0 shot) | 83.3 | Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts | - |
| SMoLA-PaLI-X Specialist | 86.3 | Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts | - |
| MoVie | 70.8 | MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond | |
| MoVie-ResNeXt | 74.9 | MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond | |
| RCN | 71.8 | TallyQA: Answering Complex Counting Questions | |
| PaLI-X-VPD | 86.2 | Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models | - |
0 of 6 row(s) selected.