Salient coding for image classification
Salient coding for image classification
复制标题
DOI：
10.1109/cvpr.2011.5995682
复制
发表时间：
2011-06
期刊：
影响因子：
--
通讯作者：
Yongzhen Huang;Kaiqi Huang;Yinan Yu;T. Tan
中科院分区：
文献类型：
--
作者：
Yongzhen Huang;Kaiqi Huang;Yinan Yu;T. Tan
基于码本的(词袋)模型是一种广泛应用的图像分类模型。我们分析了该模型中现有的编码策略，发现显著是编码的基本特征。编码的显着性意味着，如果视觉代码比其他代码更接近描述符，它将获得非常强烈的响应。在最大池化操作下的突出表现导致了在许多数据库和竞争中的最先进的性能。然而，目前的大多数编码方案没有认识到显著表示的作用，因此在表示局部描述符时可能会导致较大的偏差。在本文中，我们提出了“显著编码”，它使用描述符的最近码与其他码之间的比率来描述描述符。这种方法可以保证显著的表示而不偏离。我们在两组图像分类数据库(15-Scenes和Pascal VOC2007)上对显著编码进行了研究。实验结果表明，该方法在图像分类中的性能优于其他编码方法。
The codebook based (bag-of-words) model is a widely applied model for image classification. We analyze recent coding strategies in this model, and find that saliency is the fundamental characteristic of coding. The saliency in coding means that if a visual code is much closer to a descriptor than other codes, it will obtain a very strong response. The salient representation under maximum pooling operation leads to the state-of-the-art performance on many databases and competitions. However, most current coding schemes do not recognize the role of salient representation, so that they may lead to large deviations in representing local descriptors. In this paper, we propose “salient coding”, which employs the ratio between descriptors' nearest code and other codes to describe descriptors. This approach can guarantee salient representation without deviations. We study salient coding on two sets of image classification databases (15-Scenes and PASCAL VOC2007). The experimental results demonstrate that our approach outperforms all other coding methods in image classification.