In this paper we deal with the task of Disturbing Image Detection (DID),
exploiting knowledge encoded in Large Multimodal Models (LMMs). Specifically,
we propose to exploit LMM knowledge in a two-fold manner: first by extracting
generic semantic descriptions, and second by extracting elicited emotions.
Subsequently, we use the CLIP's text encoder in order to obtain the text
embeddings of both the generic semantic descriptions and LMM-elicited emotions.
Finally, we use the aforementioned text embeddings along with the corresponding
CLIP's image embeddings for performing the DID task. The proposed method
significantly improves the baseline classification accuracy, achieving
state-of-the-art performance on the augmented Disturbing Image Detection
dataset.

本研究通过利用大型多模型模型中编码的知识，提出了一种新的方法来解决干扰图像检测的任务。该方法通过提取通用语义描述和引发的情感来利用多模型模型中的知识，并利用 CLIP 的文本编码器获取文本嵌入。最后，将这些文本嵌入与相应的 CLIP 图像嵌入一起用于进行干扰图像检测任务，从而显著提高了基准分类准确度，达到了该领域的最新性能。