论文标题
使用全局上下文模块的快速视频对象分割
Fast Video Object Segmentation using the Global Context Module
论文作者
论文摘要
我们开发了一种实时，高质量的半监督视频对象分割算法。它的准确性与最准确，最耗时的在线学习模型相当，而其速度类似于最快的模板匹配方法，其准确性具有次优准性。模型的核心组成部分是一个新颖的全球上下文模块，可以有效地总结和传播整个视频。与以前仅使用一个帧或几个帧来指导当前帧的分割的方法相比，全局上下文模块使用了所有过去的帧。与以前最新的时空内存网络缓存在每个时空位置处的存储器不同，全局上下文模块使用固定尺寸的特征表示。因此，无论视频长度如何，它都会使用恒定的内存，并且成本较小的内存和计算。借助新型模块，我们的模型以实时速度在标准基准上实现了最高的性能。
We developed a real-time, high-quality semi-supervised video object segmentation algorithm. Its accuracy is on par with the most accurate, time-consuming online-learning model, while its speed is similar to the fastest template-matching method with sub-optimal accuracy. The core component of the model is a novel global context module that effectively summarizes and propagates information through the entire video. Compared to previous approaches that only use one frame or a few frames to guide the segmentation of the current frame, the global context module uses all past frames. Unlike the previous state-of-the-art space-time memory network that caches a memory at each spatio-temporal position, the global context module uses a fixed-size feature representation. Therefore, it uses constant memory regardless of the video length and costs substantially less memory and computation. With the novel module, our model achieves top performance on standard benchmarks at a real-time speed.
