Current architectures for multi-modality tasks such as visual question
answering suffer from their high complexity. As a result, these architectures
are difficult to train and require high computational resources. To address
these problems we present a CLIP-based architecture that does not require any
fine-tuning of the feature extractors. A simple linear classifier is used on
the concatenated features of the image and text encoder. During training an
auxiliary loss is added which operates on the answer types. The resulting
classification is then used as an attention gate on the answer class selection.
On the VizWiz 2022 Visual Question Answering Challenge we achieve 60.15 %
accuracy on Task 1: Predict Answer to a Visual Question and AP score of 83.78 %
on Task 2: Predict Answerability of a Visual Question.

该研究提出了一种基于 CLIP 的体系结构，通过将图像和文本编码器的拼接特征上应用简单的线性分类器，并在训练期间添加一项辅助损失，以操作答案类型，并将其作为答案类选择的注意力门，成功解决了多模态任务体系结构高复杂度、难以训练、计算资源要求高的问题，在 VizWiz 2022 视觉问答挑战赛上取得了 60.15％的准确率和 83.78％的平均精度分数。