YolactEdge: Real-time Instance Segmentation on the Edge

22 Dec 2020  ·  Haotian Liu, Rafael A. Rivera Soto, Fanyi Xiao, Yong Jae Lee ·

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.

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here