# YolactEdge: Real-time Instance Segmentation on the Edge

arXiv: https://arxiv.org/abs/2012.12259 · HTML: https://mlsanity.com/paper/2012.12259/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy](https://mlsanity.com/paper/2208.02049/) (2022)
- [Improving Video Instance Segmentation via Temporal Pyramid Routing](https://mlsanity.com/paper/2107.13155/) (2021)
- [Class-agnostic Reconstruction of Dynamic Objects from Videos](https://mlsanity.com/paper/2112.02091/) (2021)
- [YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems](https://mlsanity.com/paper/2408.09332/) (2024)
- [RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything](https://mlsanity.com/paper/2401.10228/) (2024)
- [Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search](https://mlsanity.com/paper/2210.01384/) (2022)
- [Circle Representation for Medical Instance Object Segmentation](https://mlsanity.com/paper/2403.11507/) (2024)
- [Monitoring social distancing with single image depth estimation](https://mlsanity.com/paper/2204.01693/) (2022)
- [Artifacts Mapping: Multi-Modal Semantic Mapping for Object Detection and 3D Localization](https://mlsanity.com/paper/2307.01121/) (2023)

## Abstract (arXiv)

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.