| DC 欄位 |
值 |
語言 |
| DC.contributor | 資訊工程學系 | zh_TW |
| DC.creator | 翁崇恒 | zh_TW |
| DC.creator | Chong-Heng Weng | en_US |
| dc.date.accessioned | 2023-7-19T07:39:07Z | |
| dc.date.available | 2023-7-19T07:39:07Z | |
| dc.date.issued | 2023 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=110526007 | |
| 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 | 物件偵測是電腦視覺中，一項重要的基礎研究項目，而近年來，Detection
Transformer(DETR)類型的模型在這項領域中脫穎而出，最終達到了state-ofthe-art 的效能水準。而這些研究在基礎的DETR 上，提出許多不同的方法，改進了原始DETR 的效能與訓練效率。
然而，我們發現DETR 類型的模型在top K query selection 的環節，可能會有陷入局部最小值的狀況，造成效能無法最佳化。為了改善這個問題，我們在top K query selection 的環節加入了噪音，鼓勵模型去探索更適合預測物件的query。我們的靈感是來自於強化學習中，有ε-greedy 這樣一種方法用來對動作加入噪音。
結合這一個加入噪音的方法以及先前的研究，在COCOval2017 上，運用
ResNet50 的backbone，我們改善了DINO +0.3AP 的效能。這個改善說明了ε-greedy 對於有效減輕陷入局部最小值的負面影響。 | zh_TW |
| dc.description.abstract | Object detection is a fundamental task in computer vision. To accomplish the object detection goal, the Detection Transformer (DETR) model has emerged as a promising approach for achieving state-of-the-art performance. Since its introduction, several variants of DETR have been proposed with the aim of improving its performance and training efficiency.
However, we find that the DETR-liked model will probably be stuck in a local minimum from top-K query selections, and hence result in inferior performance. To resolve this problem, we add noise to the DETR-liked models with top-K query selections intending to encourage the model to find better queries suitable for bounding box prediction. The rationale is that we are inspired by the ε-greedy idea usually adopted in reinforcement learning which adds noise
to action selection.
Combining this noise-adding scheme with those successful endeavors, it can improve DINO by +0.3AP with the 4 multi-scale feature maps setting on COCOval2017 using a ResNet-50 backbone. These improvements validate that the ε-greedy is effective to reduce the negative effect of being stuck in the local minimum. | en_US |
| DC.subject | 深度學習 | zh_TW |
| DC.subject | 電腦視覺 | zh_TW |
| DC.subject | 物件偵測 | zh_TW |
| DC.subject | Deep Learning | en_US |
| DC.subject | Computer Vision | en_US |
| DC.subject | Object Detection | en_US |
| DC.subject | Transformer | en_US |
| DC.title | 利用ε-greedy強化基於Transformer的物件偵 測演算法之效能 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | Performance Enhancement for Transformerbased Object Detection by ε-Greedy | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |