Neighbor-to-Neighbor Search for Fast Coding of Feature Vectors
Neighbor-to-Neighbor Search for Fast Coding of Feature Vectors
复制标题
DOI：
10.1109/iccv.2013.156
复制
发表时间：
2013-12
期刊：
影响因子：
--
通讯作者：
Nakamasa Inoue;K. Shinoda
中科院分区：
文献类型：
--
作者：
Nakamasa Inoue;K. Shinoda
将视觉代码转换为低层图像描述符，我们称之为代码分配，是基于视觉词袋（BoW）框架的图像分类算法中计算量最大的部分。本文提出了一种快速的计算方法，邻居到邻居（NTN）搜索，这种代码分配。该算法利用相邻区域的图像特征通常具有相似性的特点，有效地降低了码字与特征向量之间距离的计算代价。该方法不仅适用于矢量量化构造的硬码本（NTN-VQ），而且适用于高斯混合模型构造的软码本（NTN-GMM）。我们在PASCAL VOC 2007分类挑战任务上评估了这种方法。NTN-VQ在超向量编码中将分配成本降低了77.4%，NTN-GMM在Fisher向量编码中将其降低了89.3%，而分类性能没有任何显着下降。
Assigning a visual code to a low-level image descriptor, which we call code assignment, is the most computationally expensive part of image classification algorithms based on the bag of visual word (BoW) framework. This paper proposes a fast computation method, Neighbor-to-Neighbor (NTN) search, for this code assignment. Based on the fact that image features from an adjacent region are usually similar to each other, this algorithm effectively reduces the cost of calculating the distance between a codeword and a feature vector. This method can be applied not only to a hard codebook constructed by vector quantization (NTN-VQ), but also to a soft codebook, a Gaussian mixture model (NTN-GMM). We evaluated this method on the PASCAL VOC 2007 classification challenge task. NTN-VQ reduced the assignment cost by 77.4% in super-vector coding, and NTN-GMM reduced it by 89.3% in Fisher-vector coding, without any significant degradation in classification performance.