HalluciDet：通过特权信息为人员检测幻觉生成RGB模态
HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information
AI总结：
提出HalluciDet模型，通过利用预训练RGB检测器中的特权信息降低检测损失，实现无需RGB数据的红外到可见光图像翻译，显著提升跨模态行人检测精度。
摘要：
将视觉识别模型适应到新域的一种强大方法是通过图像翻译。然而，常见的图像翻译方法仅关注生成与目标域相同分布的数据。考虑到跨模态应用，例如航空图像中的行人检测，由于红外（IR）到可见光（RGB）图像之间的数据分布存在显著偏移，专注于生成的翻译可能会因损失集中在与任务无关的细节上而导致性能不佳。在本文中，我们提出了HalluciDet，一种用于目标检测的IR-RGB图像翻译模型。它不专注于在IR模态上重建原始图像，而是寻求降低RGB检测器的检测损失，从而避免了对RGB数据的访问需求。该模型生成一种新的图像表示，增强了场景中的目标对象，并大大提高了检测性能。我们通过实验将我们的方法与最先进的图像翻译方法和在IR上微调的方法进行了比较，结果表明，通过利用预训练RGB检测器中编码的特权信息，我们的HalluciDet在大多数情况下提高了检测精度。代码：https://github.com/heitorrapela/HalluciDet
英文摘要：
A powerful way to adapt a visual recognition model to a new domain is through image translation. However, common image translation approaches only focus on generating data from the same distribution as the target domain. Given a cross-modal application, such as pedestrian detection from aerial images, with a considerable shift in data distribution between infrared (IR) to visible (RGB) images, a translation focused on generation might lead to poor performance as the loss focuses on irrelevant details for the task. In this paper, we propose HalluciDet, an IR-RGB image translation model for object detection. Instead of focusing on reconstructing the original image on the IR modality, it seeks to reduce the detection loss of an RGB detector, and therefore avoids the need to access RGB data. This model produces a new image representation that enhances objects of interest in the scene and greatly improves detection performance. We empirically compare our approach against state-of-the-art methods for image translation and for fine-tuning on IR, and show that our HalluciDet improves detection accuracy in most cases by exploiting the privileged information encoded in a pre-trained RGB detector. Code: https://github.com/heitorrapela/HalluciDet
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
