List your company

Speech-Visual Question Answering on OK-VQA Speech-converted

29.04AccuracyUni-MoE
-1.16166.679214.5222.3608May 18, 2024

Evaluation results

MethodLinks
Uni-MoETraining Task=MoE-Task1-short-speech, Training Epochs=3 epoch2024.0529.04
Single-Modality-Expert-Task3Evaluation Protocol=zero-shot2024.0527.68
Single-Modality-Expert-Task1Evaluation Protocol=zero-shot2024.0526.58
Uni-MoETraining Task=MoE-Task1-short-speech, Training Epochs=2 epoch2024.0526.46
Uni-MoETraining Task=MoE-Task1, Training Epochs=2 epoch2024.0519.98
Uni-MoETraining Task=MoE-Task1, Training Epochs=3 epoch2024.0517.68
Single-Modality-Expert-Task6Evaluation Protocol=zero-shot2024.0514.4
Single-Modality-Expert-Task4Evaluation Protocol=zero-shot2024.0512.26
Uni-MoETraining Task=MoE-Task2, Training Epochs=2 epoch2024.058.08
Single-Modality-Expert-Task5Evaluation Protocol=zero-shot2024.053.42
Macaw-LLMEvaluation Protocol=zero-shot2024.051.06
X-InstructBLIPEvaluation Protocol=zero-shot2024.050