Browsing by Author "Ku, Wei-Lin"

Now showing 1 - 2 of 2

Discriminatively-learned Global Image Representation Using CNN as a Local Feature Extractor for Image Retrieval
(2015-01-01)
Ku, Wei-Lin
;
Chou, Hung-Chun
;
Peng, Wen-Hsiao
;
資訊工程學系
;
Department of Computer Science
This work introduces an image retrieval framework based on using deep convolutional neural networks (CNN) as a local feature extractor. Motivated by the great success of CNN in recognition tasks, one may be tempted to simply adopt the output of CNN as a global image representation for retrieval. This straightforward approach, however, has proved deficient, because it can be vulnerable to various image transformation attacks. To address this issue, we propose to treat CNN as a local feature extractor, and a local image patch selection mechanism is developed to extract discriminative patches by observing their objectness responses, aspect ratios, relative scales, and locations in the image. The criterion is given by a learned posterior probability indicating how likely the image patch in question will find a correspondence in another similar image. In addition, the CNN's weight parameters are specifically adapted by a contrastive loss function to suit retrieval tasks. Extensive experiments on typical retrieval datasets confirm the superiority of the proposed scheme over the state-of-the-art methods.
Global Image Representation Using Locality-constrained Linear Coding for Large-Scale Image Retrieval
(2014-01-01)
Wu, Yu-Hsing
;
Ku, Wei-Lin
;
Peng, Wen-Hsiao
;
Chou, Hung-Chun
;
資訊工程學系
This paper proposes a global image representation based on Locality-constrained Linear Coding (LLC), with an aim to simplify the encoding process of local descriptors so as to facilitate large-scale image retrieval. Starting from the state-of-the-art Fisher Vector (FV) representation, we replace the computation of sophisticated posterior probabilities with simpler LLC. We then conduct several empirical studies to investigate the effects and benefits of this change and to adapt the other terms in FV for a better trade-off between performance and complexity. The result is a simpler global descriptor that combines the merits of both FV and LLC. Experimental results show that when compared with other similar works, our scheme not only brings performance benefits in mean Average Precision, but also offer complexity advantages.