论文标题
向西奥多学习：合成全向室内室内数据集，用于深度转移学习
Learning from THEODORE: A Synthetic Omnidirectional Top-View Indoor Dataset for Deep Transfer Learning
论文作者
论文摘要
从角度观点来看，关于合成室内数据集的最新工作表明，卷积神经网络（CNN）对对象检测结果有了显着改善。在本文中，我们介绍了Theodore：一种新颖的大型室内数据集，其中包含100,000个高分辨率多样化的鱼眼图像，其中有14个类。为此，我们创建了客厅，不同人类角色和室内纹理的3D虚拟环境。除了捕获虚拟环境中的鱼眼图像外，我们还为语义分割，实例掩码和对象检测任务的边界框创建注释。我们将合成数据集与全面图像的最新现实数据集进行了比较。基于MS Coco权重，我们表明我们的数据集非常适合用于对象检测的微调CNN。通过图像合成和域随机化对我们的模型的高度概括，我们在高清分析数据集中的班级人员达到了高达0.84的AP。
Recent work about synthetic indoor datasets from perspective views has shown significant improvements of object detection results with Convolutional Neural Networks(CNNs). In this paper, we introduce THEODORE: a novel, large-scale indoor dataset containing 100,000 high-resolution diversified fisheye images with 14 classes. To this end, we create 3D virtual environments of living rooms, different human characters and interior textures. Beside capturing fisheye images from virtual environments we create annotations for semantic segmentation, instance masks and bounding boxes for object detection tasks. We compare our synthetic dataset to state of the art real-world datasets for omnidirectional images. Based on MS COCO weights, we show that our dataset is well suited for fine-tuning CNNs for object detection. Through a high generalization of our models by means of image synthesis and domain randomization, we reach an AP up to 0.84 for class person on High-Definition Analytics dataset.
