论文标题
SOLOV2：动态和快速实例分段
SOLOv2: Dynamic and Fast Instance Segmentation
论文作者
论文摘要
在这项工作中，我们旨在建立一个具有强大性能的简单，直接和快速的实例细分框架。我们遵循Wang等人的独奏方法的原理。 “独奏：按位置分割对象”。重要的是，我们通过动态学习对象细分器的掩模头，以便将掩盖头在位置进行调节，从而进一步迈出一步。具体而言，蒙版分支被解耦到面具内核分支和蒙版特征分支，这些分支分别负责学习卷积内核和卷积特征。此外，我们提出矩阵NMS（非最大抑制），以显着减少由于掩模的NMS引起的推理时间开销。我们的矩阵NMS一击与平行矩阵操作执行NMS，并产生更好的结果。我们演示了一个简单的直接实例分割系统，在速度和准确性方面表现出了一些最先进的方法。 SOLOV2的轻巧版本以31.3 fps执行，并产生37.1％的AP。此外，我们的最新最新结果可导致对象检测（来自我们的掩模副产品）和全景分段显示了除了实例分割外，还可以作为许多实例级识别任务的新的强基线。代码可在以下网址找到：https：//git.io/adelaidet
In this work, we aim at building a simple, direct, and fast instance segmentation framework with strong performance. We follow the principle of the SOLO method of Wang et al. "SOLO: segmenting objects by locations". Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location. Specifically, the mask branch is decoupled into a mask kernel branch and mask feature branch, which are responsible for learning the convolution kernel and the convolved features respectively. Moreover, we propose Matrix NMS (non maximum suppression) to significantly reduce the inference time overhead due to NMS of masks. Our Matrix NMS performs NMS with parallel matrix operations in one shot, and yields better results. We demonstrate a simple direct instance segmentation system, outperforming a few state-of-the-art methods in both speed and accuracy. A light-weight version of SOLOv2 executes at 31.3 FPS and yields 37.1% AP. Moreover, our state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation show the potential to serve as a new strong baseline for many instance-level recognition tasks besides instance segmentation. Code is available at: https://git.io/AdelaiDet
