MobileInst: Video Instance Segmentation on the Mobile

Video instance segmentation on mobile devices is an important yet very challenging edge AI problem. It mainly suffers from (1) heavy computation and memory costs for frame-by-frame pixel-level instance perception and (2) complicated heuristics for tracking objects. To address these issues, we present MobileInst, a lightweight and mobile-friendly framework for video instance segmentation on mobile devices. Firstly, MobileInst adopts a mobile vision transformer to extract multi-level semantic features and presents an efficient query-based dual-transformer instance decoder for mask kernels and a semantic-enhanced mask decoder to generate instance segmentation per frame. Secondly, MobileInst exploits simple yet effective kernel reuse and kernel association to track objects for video instance segmentation. Further, we propose temporal query passing to enhance the tracking ability for kernels. We conduct experiments on COCO and YouTube-VIS datasets to demonstrate the superiority of MobileInst and evaluate the inference latency on one single CPU core of the Snapdragon 778G Mobile Platform, without other methods of acceleration. On the COCO dataset, MobileInst achieves 31.2 mask AP and 433 ms on the mobile CPU, which reduces the latency by 50% compared to the previous SOTA. For video instance segmentation, MobileInst achieves 35.0 AP and 30.1 AP on YouTube-VIS 2019 & 2021.

Authors

• Renhong Zhang Huazhong University of Science and Technology
• Tianheng Cheng Huazhong University of Science and Technology
• Shusheng Yang Huazhong University of Science and Technology
• Haoyi Jiang Huazhong University of Science and Technology
• Shuai Zhang New Jersey Institute of Technology
• Jiancheng Lyu Qualcomm AI Research
• Xin Li
• Xiaowen Ying Qualcomm AI Research
• Dashan Gao Southern University of Science and Technology, Shenzhen, China Hong Kong University of Science and Technology, Hong Kong SAR, China
• Wenyu Liu
• Xinggang Wang Institute of AI, School of EIC, Huazhong University of Science and Technology

Keywords

• CV: Segmentation
• CV: Video Understanding & Activity Analysis