LLC Revisit: Scene Classification with k-Farthest Neighbours
LLC Revisit: Scene Classification with k-Farthest Neighbours
复制标题
DOI：
10.1587/transinf.2015edp7332
复制
发表时间：
2016-05
期刊：
影响因子：
--
通讯作者：
Katsuyuki Tanaka;T. Takiguchi;Y. Ariki
中科院分区：
文献类型：
--
作者：
Katsuyuki Tanaka;T. Takiguchi;Y. Ariki
本文介绍了一种简单但有效的方法，通过LLC编码过程的新方法来提高场景分类的性能。在我们提出的方法中，一个局部描述符不仅与k -最近的视觉字，但也与k -最远的视觉字编码，以产生更多的歧视性代码。由于所提出的方法是对图像分类模型的简单修改，因此它可以很容易地集成到在各个领域提出的各种现有BoF模型中，例如编码，池化，以提高其场景分类性能。使用三个场景数据集：15-Scenes，MIT-Indoor 67和Sun 367进行的实验结果表明，添加k -最远视觉词比增加k -最近视觉词的数量更好地增强了场景分类性能。
SUMMARY This paper introduces a simple but e ff ective way to boost the performance of scene classification through a novel approach to the LLC coding process. In our proposed method, a local descriptor is encoded not only with k -nearest visual words but also with k -farthest visual words to produce more discriminative code. Since the proposed method is a simple modification of the image classification model, it can be easily integrated into various existing BoF models proposed in various areas, such as coding, pooling, to boost their scene classification performance. The results of experiments conducted with three scene datasets: 15-Scenes, MIT-Indoor67, and Sun367 show that adding k -farthest visual words better enhances scene classification performance than increasing the number of k -nearest visual words.