E-VQA
This dataset, adapted from VQAv2, is designed for the Visual Question Answering task and evaluates multimodal model editing in terms of reliability, stability and generality. You can download the dataset from here
This dataset, adapted from VQAv2, is designed for the Visual Question Answering task and evaluates multimodal model editing in terms of reliability, stability and generality. You can download the dataset from here