论文标题
使用式剪辑指导使用stylegan的fly对象检测
On-the-fly Object Detection using StyleGAN with CLIP Guidance
论文作者
论文摘要
我们提出了一个完全自动化的框架，用于在卫星图像上构建对象探测器，而无需任何人类注释或干预。我们通过利用现代生成模型（例如StyleGan）的合并力量以及多模式学习（例如剪辑）的最新进展来实现这一目标。虽然深层生成模型有效地编码了与数据分布相关的关键语义，但对于下游任务（例如对象检测），该信息无法立即访问。在这项工作中，我们利用了剪贴画将图像功能与文本说明相关联的能力，以识别发电机网络中的神经元，后来被用于构建直率的检测器。
We present a fully automated framework for building object detectors on satellite imagery without requiring any human annotation or intervention. We achieve this by leveraging the combined power of modern generative models (e.g., StyleGAN) and recent advances in multi-modal learning (e.g., CLIP). While deep generative models effectively encode the key semantics pertinent to a data distribution, this information is not immediately accessible for downstream tasks, such as object detection. In this work, we exploit CLIP's ability to associate image features with text descriptions to identify neurons in the generator network, which are subsequently used to build detectors on-the-fly.
