Video instance segmentation (VIS) is the task that requires simultaneously classifying, segmenting and tracking object instances of interest in video. Recent methods typically develop sophisticated pipelines to tackle this task. Here, we propose a new video instance segmentation framework built upon Transformers, termed VisTR, which views the VIS task as a direct end-to-end parallel sequence decoding/prediction problem. Given a video clip consisting of multiple image frames as input, VisTR outputs the sequence of masks for each instance in the video in order directly. At the core is a new, effective instance sequence matching and segmentation strategy, which supervises and segments instances at the sequence level as a whole. VisTR frames the instance segmentation and tracking in the same perspective of similarity learning, thus considerably simplifying the overall pipeline and is significantly different from existing approaches. Without bells and whistles, VisTR achieves the highest speed among all existing VIS models, and achieves the best result among methods using single model on the YouTube-VIS dataset. For the first time, we demonstrate a much simpler and faster video instance segmentation framework built upon Transformers, achieving competitive accuracy. We hope that VisTR can motivate future research for more video understanding tasks.
翻译:视频例谱分割( VisTR) 是一项任务, 需要同时对视频中感兴趣的对象进行分类、 分割和跟踪。 最近的方法通常会开发复杂的管道, 以完成这项任务。 在这里, 我们提议一个新的视频例分割框架, 以变异器为基础, 称为 VisTR, 将VIS 任务视为直接端到端平行的平行序列解码/ 准备问题。 视频片段包含多个图像框作为输入, VisTR 输出视频中每个例子的遮罩序列, 直接顺序。 核心是一个新的、 有效实例序列匹配和分割战略, 对整个序列级别进行监管。 VisTR 以类似学习的相同角度将试样分割和跟踪设置为框架, 从而大大简化整个管道, 并且与现有方法大不相同 。 没有钟和哨子, VisTR 就能实现所有现有 VISS 模型中的最高速度, 并实现在YouTube- VIS 数据集上使用单一模型的方法取得最佳结果 。 第一次, 我们展示了一个更简单、 更快的视频例分割框架, 能够在未来对变异性任务进行更敏化。