As AI-generated image (AIGI) methods become more powerful and accessible, it
has become a critical task to determine if an image is real or AI-generated.
Because AIGI lack the signatures of photographs and have their own unique
patterns, new models are needed to determine if an image is AI-generated. In
this paper, we investigate the ability of the Contrastive Language-Image
Pre-training (CLIP) architecture, pre-trained on massive internet-scale data
sets, to perform this differentiation. We fine-tune CLIP on real images and
AIGI from several generative models, enabling CLIP to determine if an image is
AI-generated and, if so, determine what generation method was used to create
it. We show that the fine-tuned CLIP architecture is able to differentiate AIGI
as well or better than models whose architecture is specifically designed to
detect AIGI. Our method will significantly increase access to AIGI-detecting
tools and reduce the negative effects of AIGI on society, as our CLIP
fine-tuning procedures require no architecture changes from publicly available
model repositories and consume significantly less GPU resources than other AIGI
detection models.

通过对大规模互联网数据集进行预训练后，在真实图像和人工智能生成图像进行微调，我们展示了细调后的 Contrastive Language-Image Pre-training（CLIP）架构能够与专门设计用于检测人工智能生成图像的模型相媲美甚至更好地区分人工智能生成图像，并且能够确定生成方法。我们的方法将显著提高人工智能生成图像检测工具的可用性，减少人工智能生成图像对社会的负面影响，因为我们的 CLIP 微调过程不需要对公开可用模型仓库进行架构更改，而且消耗的 GPU 资源明显更少。

通过 CLIP 检测人工智能生成的图像

Detecting AI-Generated Images via CLIP

A wide range of control perspectives have been explored in controllable text
generation. Structure-controlled summarization is recently proposed as a useful
and interesting research direction. However, current structure-controlling
methods have limited effectiveness in enforcing the desired structure. To
address this limitation, we propose a sentence-level beam search generation
method (SentBS), where evaluation is conducted throughout the generation
process to select suitable sentences for subsequent generations. We experiment
with different combinations of decoding methods to be used as subcomponents by
SentBS and evaluate results on the structure-controlled dataset MReD.
Experiments show that all explored combinations for SentBS can improve the
agreement between the generated text and the desired structure, with the best
method significantly reducing the structural discrepancies suffered by the
existing model, by approximately 68%.

本文提出了一种基于句子级别的 beam search 方法的生成方法（SentBS），其中在生成过程中进行评估以选择适合后续生成的句子，旨在提高结构受控文本生成的效果，实验证明该方法可显著减少现有模型所遭受的约 68％的结构差异，并在结构控制的 MReD 数据集上取得了良好的效果。