AutoPose：搜索多尺度分支聚合用于姿态估计
AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation
摘要：
我们提出了AutoPose，这是一种新型的神经架构搜索（NAS）框架，能够自动发现跨尺度连接的多个并行分支，以实现准确和高分辨率的2D人体姿势估计。最近，用于姿态估计的高性能手工卷积网络显示出对多尺度融合和高分辨率表示的需求不断增长。然而，目前的NAS工作表现出有限的灵活性的规模搜索，他们主要采用简化的搜索空间的单分支结构。这种简化限制了不同尺度信息的融合，并且无法保持高分辨率的表示。所呈现的AutoPose框架能够搜索多分支尺度和网络深度，以及细胞级微观结构。在搜索空间的启发下，提出了一种新的双层优化方法，其中网络级结构通过强化学习进行搜索，单元级结构通过基于梯度的方法进行搜索.在2.5 GPU天内，AutoPose能够在MS COCO数据集上找到非常有竞争力的架构，这些架构也可以转移到MPII数据集。我们的代码可在https://github.com/VITA-Group/AutoPose上获得。
英文摘要：
We present AutoPose, a novel neural architecture search(NAS) framework that is capable of automatically discovering multiple parallel branches of cross-scale connections towards accurate and high-resolution 2D human pose estimation. Recently, high-performance hand-crafted convolutional networks for pose estimation show growing demands on multi-scale fusion and high-resolution representations. However, current NAS works exhibit limited flexibility on scale searching, they dominantly adopt simplified search spaces of single-branch architectures. Such simplification limits the fusion of information at different scales and fails to maintain high-resolution representations. The presentedAutoPose framework is able to search for multi-branch scales and network depth, in addition to the cell-level microstructure. Motivated by the search space, a novel bi-level optimization method is presented, where the network-level architecture is searched via reinforcement learning, and the cell-level search is conducted by the gradient-based method. Within 2.5 GPU days, AutoPose is able to find very competitive architectures on the MS COCO dataset, that are also transferable to the MPII dataset. Our code is available at https://github.com/VITA-Group/AutoPose.
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。
