BlockCopy：采用块稀疏特征传播和在线策略的高分辨率视频处理
BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies
摘要：
在本文中，我们提出了BlockCopy，这是一种与标准逐帧处理相比，加速预训练的基于帧的CNN更有效地处理视频的方案。为此，轻量级策略网络确定图像中的重要区域，并使用自定义块稀疏卷积仅对选定区域应用操作。非选定区域的特征仅从前一帧复制，从而减少计算次数和延迟。执行策略是使用强化学习以在线方式训练的，而不需要地面实况注释。我们的通用框架在密集预测任务上进行了演示，例如行人检测，实例分割和语义分割，使用最先进的技术（中心和规模预测器，MGAN，SwiftNet）和标准基线网络（Mask-RCNN，DeepLabV 3+）。BlockCopy实现了显著的FLOPS节省和推理加速，对准确性的影响最小。
英文摘要：
In this paper we propose BlockCopy, a scheme that accelerates pretrained frame-based CNNs to process video more efficiently, compared to standard frame-by-frame processing. To this end, a lightweight policy network determines important regions in an image, and operations are applied on selected regions only, using custom block-sparse convolutions. Features of non-selected regions are simply copied from the preceding frame, reducing the number of computations and latency. The execution policy is trained using reinforcement learning in an online fashion without requiring ground truth annotations. Our universal framework is demonstrated on dense prediction tasks such as pedestrian detection, instance segmentation and semantic segmentation, using both state of the art (Center and Scale Predictor, MGAN, SwiftNet) and standard baseline networks (Mask-RCNN, DeepLabV3+). BlockCopy achieves significant FLOPS savings and inference speedup with minimal impact on accuracy.
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。
