基于卷积词袋网络的视觉识别  

Bag of convolutional words networks for visual recognition

作　　者：薛昆南 薛月菊[1] 毛亮[1] 刘洪山[1] XUE Kunnan;XUE Yueju;MAO Liang;LIU Hongshan(School of Electronic Engineering, South China Agricultural University, Guangzhou 510642, China)

机构地区：[1]华南农业大学电子工程学院,广州510642

出　　处：《计算机工程与应用》2016年第21期180-187,共8页Computer Engineering and Applications

基　　金：国家自然科学基金委员会-广东联合基金(No.U1301253);广东省科技计划项目(No.2014A020208108)

摘　　要：近年来,卷积神经网络(CNN)凭借其强大的特征学习能力在视觉识别领域取得重要进展。针对CNN全连接层对图像平移、旋转、缩放等变换比较敏感的问题,提出了一种混合模型——卷积词袋网络(Bo CW-Net)。它将Bo W模型嵌入CNN结构中并代替全连接层,通过端到端的方式学习特征、字典和分类器。为实现Bo CW-Net整个网络的有监督学习,提出基于方向相似度的Bo CW编码。同时,为充分利用中层特征和高层特征的鉴别性,将中层辅助分类器与高层分类器集成,形成主-辅集成分类器。实验结果表明:相比全连接层,Bo CW表示对各种变换具有更强的不变性;主-辅集成分类器能有效融合中层、高层特征,提高Bo CW-Net的识别性能;相比新近发展的CNN模型,Bo CW-Net在CIFAR-10、CIFAR-100和MNIST数据库上均取得了改进的识别性能,最终分别获得4.88%、22.48%和0.21%的测试错误率。In recent years, Convolutional Neural Networks(CNN)have made a progress in visual recognition tasks with its powerful feature learning ability. A hybrid model called BoCW-Net is proposed to solve the problem that full-connection layer in CNN is more sensitive to image’s transformations such as translation, rotation and scale, et al. It embeds BoW model into CNN architectures and replaces the full-connection layer, while it can learn feature, dictionary and classifier in the end-to-end way. In order to realize supervised learning of whole BoCW-Net, BoCW encoding based on direction similarity is proposed. In the meanwhile, to take full advantage of the discrimination of both mid-level and high-level features,middle-level auxiliary classifier is integrated to high-level classifier to form the main-auxiliary ensemble classifier. Experimental results show that BoW model imbedded into CNN has better invariance for a variety of transformations compared with the full-connection layer. Main-auxiliary ensemble classifier can effectively fusion mid-level and high-level features to improve the recognition performance of BoCW-Net. Compared with the newly developed CNN models, BoCW-Net acquires improved recognition performance on CIFAR-10、CIFAR-100 and MNIST dataset with 4.88%, 22.48% and 0.21% final test error rate, respectively.

关 键 词：卷积神经网络 卷积词袋(BoCW)表示 主-辅集成分类器 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]