Deep co-occurrence feature learning for visual object recognition

Ya Fang Shih, Yang Ming Yeh, Yen Yu Lin, Ming Fang Weng, Yi Chang Lu, Yung Yu Chuang

研究成果: Chapter同行評審

35 引文 斯高帕斯(Scopus)

摘要

This paper addresses three issues in integrating part-based representations into convolutional neural networks (CNNs) for object recognition. First, most part-based mod-els rely on a few pre-specified object parts. However, the optimal object parts for recognition often vary from cat-egory to category. Second, acquiring training data with part-level annotation is labor-intensive. Third, modeling spatial relationships between parts in CNNs often involves an exhaustive search of part templates over multiple net-work streams. We tackle the three issues by introducing a new network layer, called co-occurrence layer. It can ex-tend a convolutional layer to encode the co-occurrence be-tween the visual parts detected by the numerous neurons, instead of a few pre-specified parts. To this end, the feature maps serve as both filters and images, and mutual correla-tion filtering is conducted between them. The co-occurrence layer is end-to-end trainable. The resultant co-occurrence features are rotation-and translation-invariant, and are ro-bust to object deformation. By applying this new layer to the VGG-16 and ResNet-152, we achieve the recogni-tion rates of 83.6% and 85.8% on the Caltech-UCSD bird benchmark, respectively. The source code is available at https://github.com/yafangshih/Deep-COOC.
原文American English
主出版物標題2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
發行者Institute of Electrical and Electronics Engineers Inc.
頁面7302-7311
頁數10
ISBN(列印)9781538604571
DOIs
出版狀態Published - 6 11月 2017

出版系列

名字Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
2017-January

指紋

深入研究「Deep co-occurrence feature learning for visual object recognition」主題。共同形成了獨特的指紋。

引用此