物件偵測方法及電子裝置

專利類型

發明

專利國別 (專利申請國家)

中華民國

專利申請案號

111124468

專利證號

I 809957

專利獲證名稱

物件偵測方法及電子裝置

專利所屬機關 (申請機關)

國立臺灣科技大學

獲證日期

2023/07/21

技術說明

本創作提出了基於輕量稀疏模型整合知識蒸餾優化深度網路於即時物件偵測系統，是一種基於卷積神經網路架構進行改良之物件偵測技術，其採用EfficientNet lite[1]、Path Aggregation Network[2]和Generalized Focal Loss v2[11]來分別作為卷機神經網路的骨幹(backbone)、頸部(neck)和頭部(head)，並搭配馬賽克資料增強法[10]、GIoU loss[13]、混合精度訓練[14]以及標籤平滑來訓練此輕量稀疏模型。另外，為提升輕量網路在物件偵測精度不足的問題，本創作在頭部的邊界框分支使用位置蒸餾技術，透過老師與學生模型的互相訓練能有效提升學生網路的推理準確率，且不會在推理時增加額外計算需求。此外，本創作使用 NVIDIA Apex (A PyTorch Extension)[12]擴充套件下的 ASP(Automatic Sparsity)模組生成50%稀疏性網路，並可以支援在NVIDIA Tensor Core上進行硬體層級加速，提升推論的速度。在利用稀疏性網路生成的技術時，可以先將原始網路訓練到一定的階段，然後在進行稀疏性網路生成和稀疏性網路的再訓練，可以避免一開始過早遮罩權重導致訓練收斂受到過大的影響，在網路收斂較穩定後再利用稀疏性網路生成提高練速度與訓練精度。 In this study, a refined and light-weight model is proposed using network sparsity and knowledge distillation for real-time object detection. The implemented model is characterized by its excellent performance in object detection and good compatibility with the standalone machines. There are several designs integrated into the proposed framework to accomplish light-weight models, inference speed up, and high performance in object detection. The sparse and light-weight structure was chosen as the network’s backbone, and feature fusion is performed by the modified feature pyramid networks. Thus, the crucial features in the complex objects or scenes can still be extracted by the model effectively and efficiently. In addition, the learning strategies of data augmentation, mixed precision training, and network sparsity are adopted to enhance the generalization for the light-weight model, and subsequently boost the performance. Moreover, the knowledge distillation is further applied to tackle the significant performance dropping issue when models are lighter. The performance of the light-weight model is further boosted via the student-teacher learning without the burden of extra execution time. As a result, from the perspective of deployment, the proposed light-weight model with high detection performance is competitive in reducing the hardware barrier when using the deep learning models. In this study, the public dataset of MS-COCO 2017 was used for performance assessment and comparison. Experimental results show that the implemented light-weight model not only maintains high detection performance but also accelerates the inference efficiency to achieve real-time detection, making the deployment more promising.

備註

連絡單位 (專責單位/部門名稱)

技術移轉中心

連絡電話

02-2733-3141#7346

網址