多任务正交切线规则AET用于暗目标检测
Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection
摘要：
黑暗环境中由于光子数量不足和噪声干扰，使得计算机视觉算法面临挑战。为了提高在黑暗环境中的目标检测，我们提出了一种新的多任务自动编码变换（MAET）模型，它能够探索背后的照明转换的内在模式。在一个自我监督的方式，MAET学习的内在视觉结构的编码和解码的现实照明退化的转换，考虑到物理噪声模型和图像信号处理（ISP）。在此基础上，我们通过解码限界框坐标和类来实现目标检测任务。为了避免两个任务的过度纠缠，我们的MAET通过施加正交切线规则来解开对象和退化特征。这形成了一个参数流形，沿着该流形，可以通过最大化沿着各个任务的输出的切线之间的正交性来几何地制定多任务预测。我们的框架可以基于主流的目标检测架构实现，并使用正常的目标检测数据集（如VOC和COCO）直接进行端到端训练。我们使用合成和真实世界的数据集实现了最先进的性能。代码可在https://github.com/cuiziteng/MAET上获得。
英文摘要：
Dark environment becomes a challenge for computer vision algorithms owing to insufficient photons and undesirable noise. To enhance object detection in a dark environment, we propose a novel multitask auto encoding transformation (MAET) model which is able to explore the intrinsic pattern behind illumination translation. In a self-supervision manner, the MAET learns the intrinsic visual structure by encoding and decoding the realistic illumination-degrading transformation considering the physical noise model and image signal processing (ISP). Based on this representation, we achieve the object detection task by decoding the bounding box coordinates and classes. To avoid the over-entanglement of two tasks, our MAET disentangles the object and degrading features by imposing an orthogonal tangent regularity. This forms a parametric manifold along which multitask predictions can be geometrically formulated by maximizing the orthogonality between the tangents along the outputs of respective tasks. Our framework can be implemented based on the mainstream object detection architecture and directly trained end-to-end using normal target detection datasets, such as VOC and COCO. We have achieved the state-of-the-art performance using synthetic and real-world datasets. Code is available at https://github.com/cuiziteng/MAET.
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。
