| DC 欄位 |
值 |
語言 |
| DC.contributor | 資訊工程學系 | zh_TW |
| DC.creator | 張育珉 | zh_TW |
| DC.creator | Yu-Min Zhang | en_US |
| dc.date.accessioned | 2021-8-2T07:39:07Z | |
| dc.date.available | 2021-8-2T07:39:07Z | |
| dc.date.issued | 2021 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=108522036 | |
| dc.contributor.department | 資訊工程學系 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.abstract | 由於高階的GPU始終定價較高體積較大的等一些較高的門檻，開發輕量級的物件偵測器至關重要，為了減少計算資源的無謂損耗，如何降低冗餘的計算起著重要的作用。本論文提出了一種全新的輕量級卷積方法Cross-Stage Lightweight(CSL) Module，它以廉價的運算來生成較為冗餘的特徵圖。在中間擴展深度的階段，我們將過去使用的pointwise convolution更換為depthwise convolution以生成候選的特徵圖。我們提出的CSL-Module可以顯著地降低計算成本，在CIFAR-10上進行的實驗表明了CSL-Module可以逼近convolution-3x3的擬合能力。最後我們以CSL-Module及其衍伸模組為基礎建構了全新的輕量級物件偵測器CSL-YOLO，與Tiny-YOLOv4相比，在MS-COCO上進行的實驗表明了CSL-YOLO僅以其43% FLOPs和52% parameters即可達到更好的物件偵測性能，達到了state-of-the-art的水準。 | zh_TW |
| dc.description.abstract | The development of lightweight object detectors is essential due to the limited computation resources. To reduce the computation cost, how to generate redundant features plays a significant role. This paper proposes a new lightweight Convolution method Cross-Stage Lightweight (CSL) Module, to generate redundant features from cheap operations. In the intermediate expansion stage, we replaced Pointwise Convolution with Depthwise Convolution to produce candidate features. The proposed CSL-Module can reduce the computation cost significantly. Experiments conducted at MS-COCO show that the proposed CSL-Module can approximate the fitting ability of Convolution-3x3. Finally, we use the module to construct a lightweight detector CSL-YOLO, achieving better detection performance with only 43% FLOPs and 52% parameters than Tiny-YOLOv4. | en_US |
| DC.subject | 輕量級物件偵測器 | zh_TW |
| DC.subject | YOLO | en_US |
| DC.subject | MS-COCO | en_US |
| DC.title | 用於邊緣計算的全新輕量化物件偵測系統 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | CSL-YOLO: A New Lightweight Object Detection System for Edge Computing | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |