基於網路社群分享資源之圖像語意擴充來增進圖像分類效能

Learning by Expansion: Exploiting Web Resources for Image Classification with Few Training Examples

王聖媛(Sheng-Yuan Wang)

指導教授 ： 徐宏民

國立臺灣大學/電機資訊學院/資訊工程學研究所/碩士(2010年)

https://doi.org/10.6342/NTU.2010.10197

摘要

無資料

關鍵字

物件辨識 ； 圖像分類 ； 網路圖片搜尋 ； 語意擴充 ； 群眾外包

並列摘要

Witnessing the sheer amount of user-contributed photos and videos, we argue to leverage such freely available image collections as the training images for image classification. We propose an image expansion framework to mine more semantically related training images provided very few training examples. The expansion is based on a semantic graph considering both visual and (noisy) textual similarities in the auxiliary image collections, where we also consider scalability issues (e.g., MapReduce) as constructing the graph. We found the expanded images not only reduce the time-consuming annotation efforts but also further improve the classification accuracy since including more visually diverse training images given the limited training images. Experimenting in certain benchmarks, we show that the expanded training images improve image classification significantly. Furthermore, we can achieve more than 25% relative improvement in accuracy compared to existing state-of-the-art methods similarly aiming to mine training images from such media sharing services (i.e., Flickr).

並列關鍵字

Object Recognition ； Image Classification ； Web Image Search ； Crowdsourcing ； Semantic Query Expansion

參考文獻

and D. A. Forsyth. Names and faces in the news. In CVPR (2), pages 848–854, 2004.

2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,

pages 1463–1470, Washington, DC, USA, 2006. IEEE Computer Society.

[3] A. Blum and T. Mitchell. Combining labeled and unlabeled data with co-training. In

[4] A. Bosch, A. Zisserman, and X. Munoz. Representing shape with a spatial pyramid