Swift Concurrent Semantic Segmentation and Object Detection on Edge Devices

Chih Chung Hsu, Yun Zhong Jiang, Wei Hao Huang

研究成果: Conference contribution

摘要

We propose a real-time network optimized for joint semantic segmentation and object detection on edge devices. Our architecture builds on the latest YOLO series network and incorporates lightweight segmentation sub-networks for multi-task learning. Specifically, we leverage layers two to four of the YOLO network, which contain substantial semantic information at varying resolutions, to segment objects of diverse sizes. We introduce the Parallel Aggregation Pyramid Pooling Module (PAPPM) to efficiently generate buffered semantic segmentation feature maps by utilizing single-point addition and residual learning. This approach reduces computational complexity and memory usage without compromising accuracy. We also propose a novel Progressively Iterative Learning (PIL) approach to learn the weights for the backbone, neck, and multi-task heads, respectively, without catastrophic forgetting. Our approach achieves state-of-the-art performance on benchmark datasets, demonstrating the effectiveness of our proposed techniques.

原文English
主出版物標題Proceedings - 2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023
發行者Institute of Electrical and Electronics Engineers Inc.
頁面40-45
頁數6
ISBN(電子)9798350313154
DOIs
出版狀態Published - 2023
事件2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023 - Brisbane, Australia
持續時間: 2023 7月 102023 7月 14

出版系列

名字Proceedings - 2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023

Conference

Conference2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023
國家/地區Australia
城市Brisbane
期間23-07-1023-07-14

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 電腦科學應用
  • 電腦視覺和模式識別
  • 媒體技術
  • 控制和優化

指紋

深入研究「Swift Concurrent Semantic Segmentation and Object Detection on Edge Devices」主題。共同形成了獨特的指紋。

引用此