請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/2295
標題: | 減緩卷積類神經網路之災難性失憶問題以有效達成物體辨識 Mitigate Catastrophic Forgetting in Convolutional Neural Networks for Effective Instance Recognition |
作者: | Da-Fang Ke 柯達方 |
指導教授: | 羅仁權(Ren C. Luo) |
關鍵字: | 漸進式學習,深度學習,災難性失憶,物體辨識, incremental learning,deep learning,catastrophic forgetting,instance recognition, |
出版年 : | 2017 |
學位: | 碩士 |
摘要: | 物體辨識為電腦視覺中一項十分重要的研究主題,在機器人中為建立認知系統的重要橋梁,機器人必須能在多變的視覺回饋下萃取有用的特徵,進而轉化為高階的知識語言,才能夠實行一連串複雜的任務,在近年由Alex Krizhevsky成功的將深度捲積網路(Deep Convolutional Neural Networks)實現並應用在影像分類上後,許多的辨識問題有了突破性的發展,然而,儘管有強健穩定的辨識能力,要實現完整的智慧機器人尚有許多實際層面的考量需要克服。
本篇論文探討以漸進式學習(incremental learning)的方式來達到物體辨識,機器人在特定的工作環境中往往需要強健穩定的辨識能力來區分影像中不同狀況下的物體 (例如尺度、亮度、遮蔽變化等),藉由目前深度學習的方法且在資料充裕的情況下,我們可以得到強健可依賴的辨識系統,然而,其中最大的問題是完整的影像資料在實際中是不存在的,影像資料的收集與標籤化是循序漸進的過程,因此,我們需要發展一個能夠漸進式的學習方法來反映這樣的需求,再者,我們希望漸進式學習能夠模仿人類的學習模式,在學習新的知識時,可以無需無過往資料的再檢視,而能夠在保有原有知識下再學習新的知識,此最大的好處即是我們不需儲存非常大量的影像資料,這對於工作於不同環境中的可適應性的機器人來說是非常具有其效益性的。 根據我們所想的學習情境當中,最大的困難是如何克服”災難性失憶(catastrophic forgetting)”,災難性失憶是由於類神經網路在學習新的資訊時,新學習的知識將會複寫掉之前學習過的知識,反觀人類的學習,人類只會輕微的遺忘而非如此嚴重的失憶,為模仿這樣的學習模式,我們運用知識萃取當中的一項技術-Pseudorehearsal作為訓練的機制,並貢獻了兩個能大幅增進表現的想法及理論,第一是引入了imaging recollection,模仿人腦對某物體映像的概念,另神經網路自行得到最能反映某物體特徵的影像;第二則是提出pseudo neurons,使在漸進式的訓練過程中,確保在網路最後一層的新類別神經元能夠藉由合理正確的損失函數來訓練,論文所提出的演算法能夠很好的在學習新的物體及保有過往學過的物體間取得很好的平衡點。藉由完整的實驗我們印證所提出的演算法的可行性並分析及討論,同時也比較其他方法來凸顯我們方法的成效。 Object recognition has remained an important research topic in computer vision for a long time. It plays a critical role in the area of robotics. Robots need to extract useful information from rich visual feedback and convert it to high-level semantic knowledge, and hence can lead to intelligence. However, until the emerging of Convolutional Neural Networks (CNNs), the fundamental ability to recognize objects is still insufficient. Since Alex Krizhevsky successfully applied deep CNNs on large scale image classification, CNNs has been bringing lots of success in the community of computer vision. Yet, lots of practical concerns still need to be overcome to make intelligent systems truly useful. In this thesis, we focus on a practical issue which requires robots to be able to incrementally learn new objects. We first reason that an intelligent service robot working in a particular environment needs to recognize instances under different imaging conditions (scale, brightness, occlusion, etc.). Through the advanced deep learning method, we are able to train a reliable visual system given sufficient data. The issue, however, is that in the reality of beginning, a complete dataset that covers all instances to be learned and provides sufficient imaging conditions is unavailable. In practice, supervisors collect new data and train recognition systems repeatedly and incrementally. It is necessary to derive an incremental learning approach to meet this requirement. A direct solution would be to reuse of every past data along with new data to ensure performance. While this may be workable, it requires a reservoir of persistent training data for all learning stage, an assumption which may not always hold. To this end, we investigate instance recognition in continuous learning scenarios without the need to access previous data. Under the hood, we are investigating how to mitigate catastrophic forgetting. Catastrophic forgetting is a phenomenon which destroys previously learned knowledge when training Neural Networks on new data. In the thesis, we propose pseudorehearsal with imaging recollection and pseudo neurons to address the forgetting problem. Our approach can achieve a promising tradeoff between learning new knowledge and preserving old knowledge. We demonstrate the feasibility of our approach by experiments and comparison with other approaches. We also provide insights to understand our innovation by experimental analysis. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/2295 |
DOI: | 10.6342/NTU201703298 |
全文授權: | 同意授權(全球公開) |
顯示於系所單位: | 電機工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-106-1.pdf | 8.34 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。