{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/yolactedge-real-time-instance-segmentation-on","title":"YolactEdge: Real-time Instance Segmentation on the Edge","arxiv_id":"2012.12259","date":"2020-12-22","proceeding":null,"authors":["Haotian Liu","Rafael A. Rivera Soto","Fanyi Xiao","Yong Jae Lee"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2012.12259v2","url_pdf":"https://arxiv.org/pdf/2012.12259v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"yolactedge-real-time-instance-segmentation-on","repo_url":"https://github.com/haotian-liu/yolact_edge","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"yolactedge-real-time-instance-segmentation-on","repo_url":"https://github.com/fanzhemeng/yolact_edge-myver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"real-time-instance-segmentation","task_name":"Real-time Instance Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.12259","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}