论文标题
yolactegge：边缘的实例实例分割
YolactEdge: Real-time Instance Segmentation on the Edge
论文作者
论文摘要
我们提出了YolactEdge，这是一种以实时速度在小边缘设备上运行的第一种竞争实例细分方法。具体而言，Yolactedge在Jetson Agx Xavier（在RTX 2080 TI上的172.7 fps）上以高达30.8 fps的速度运行，并在550x550分辨率图像上具有RESNET-101骨架。为了实现这一目标，我们对基于图像的最先进的实时方法yolact进行了两次改进：（1）在仔细换档速度和准确性的同时，应用张力优化，以及（2）一个新颖的功能翘曲模块来利用视频中的时间冗余性。 YouTube VIS和MS可可数据集的实验表明，Yolactedge在现有的实时方法上产生3-5倍的速度，同时产生竞争性掩码和盒子检测准确性。我们还进行消融研究以剖析我们的设计选择和模块。代码和型号可在https://github.com/haotian-liu/yolact_edge上找到。
We propose YolactEdge, the first competitive instance segmentation approach that runs on small edge devices at real-time speeds. Specifically, YolactEdge runs at up to 30.8 FPS on a Jetson AGX Xavier (and 172.7 FPS on an RTX 2080 Ti) with a ResNet-101 backbone on 550x550 resolution images. To achieve this, we make two improvements to the state-of-the-art image-based real-time method YOLACT: (1) applying TensorRT optimization while carefully trading off speed and accuracy, and (2) a novel feature warping module to exploit temporal redundancy in videos. Experiments on the YouTube VIS and MS COCO datasets demonstrate that YolactEdge produces a 3-5x speed up over existing real-time methods while producing competitive mask and box detection accuracy. We also conduct ablation studies to dissect our design choices and modules. Code and models are available at https://github.com/haotian-liu/yolact_edge.
