弱監督式卷積網路轉移在場景剖析的應用

Transferring Weakly-Supervised Convolutional Networks for Scene Parsing

王任(Wang, Ren)

指導教授 ： 陳煥宗

國立清華大學/電機資訊學院/資訊工程學系/碩士(2015年)

摘要

深度神經網路近幾年在電腦視覺領域變得越來越熱門，最主要的原因在於其強大的特徵擷取能力。而在深度神經網路中，轉移學習對於避免過度擬合扮演了一個很重要的角色。在本篇論文裡，我們提出了一個基於分群的方法來整合完整標籤資料與弱標籤資料，並用這些資料來訓練一個卷積網路。透過轉移學習，這樣的卷積網路可以用來當作其他目標任務的預訓練模型。接著，我們設計了一個針對影像剖析問題的卷積網路架構來驗證我們的想法。初步的實驗結果顯示這樣的預訓練卷積網路可以有效地應用於轉移學習。

關鍵字

卷積網路 ； 轉移學習 ； 弱標籤資料 ； 場景剖析

並列摘要

Deep neural networks have become more and more popular in computer vision because of their powerful ability to extract distinctive image features. In deep neural networks, transfer learning plays an important role to avoid overfitting. In this thesis, we present a clustering-based method to combine fully-labeled data with weakly-labeled data for convolutional networks. By transfer learning, these convolutional networks can be viewed as pre-trained models for another target task. Next, we design a framework of convolutional networks for scene parsing to demonstrate our idea. Preliminary experimental results show that it is helpful to use these pre-trained convolutional networks for transfer learning.

並列關鍵字

convolutional networks ； transfer learning ； weakly-labeled data ； scene parsing

參考文獻

[1] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua,

and Sabine Susstrunk. SLIC superpixels compared to state-of-the-art superpixel

methods. IEEE Trans. Pattern Anal. Mach. Intell., 34(11):2274{2282, 2012.

learning. In Unsupervised and Transfer Learning - Workshop held at ICML 2011,

[3] Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen