ID 原文 译文
24205 利用卷积定理在频域中实现空域线性卷积被认为是一种非常有效的实现方式，该文首先提出一种统一的基于时域抽取方法的分裂基-2/(2a) 1 维 FFT 快速算法，其中 a 为任意自然数，然后在 CPU 环境下对提出的 FFT 算法在一类卷积神经网络中的加速性能进行了比较研究。 Convolution theorem provides a very effective way to implement a linear convolution in spatial domain by multiplication in frequency domain. This paper proposes an unified one-dimensional FFT algorithm based on decimation-in-time split- radix-2/(2a), in which a is an arbitrary natural number. The acceleration performance of convolutional neural network is studied by using the proposed FFT algorithm on CPU environment.
24206 在 MNIST手写数字数据库以及 Cifar-10 对象识别数据集上的实验表明：利用分裂基-2/4 FFT 算法和基-2 FFT 算法实现的卷积神经网络相比于空域直接实现的卷积神经网络，精度并不会有损失，并且分裂基-2/4 能取得最好的提速效果，在以上两个数据集上分别提速 38.56%和 72.01%。 Experimental results on the MNIST database and Cifar-10 database show great improvement when compared to the direct linear convolution based CNN with no loss in accuracy, and the radix-2/4 FFT gets the best time savings of 38.56% and 72.01% respectively.
24207 因此，在频域中实现卷积神经网络的线性卷积操作是一种十分有效的实现方式。 Therefore, it is a very effective way to realize linear convolution operation in frequency domain.
24208 为避免传统谱聚类算法高复杂度的应用局限，基于地标表示的谱聚类算法利用地标点与数据集各点间的相似度矩阵，有效降低了谱嵌入的计算复杂度。 The applicability of traditional spectral clustering is limited by its high complexity in large-scale data sets. Through construction of affinity matrix between landmark points and data points, the Landmark-based Spectral Clustering (LSC) algorithm can significantly reduce the computational complexity of spectral embedding.
24209 在大数据集情况下，现有的随机抽取地标点的方法会影响聚类结果的稳定性，k 均值中心点方法面临收敛时间未知、反复读取数据的问题。 It is vital for clustering results to apply the suitable strategies of the generation of landmark points. While considering big data problems, the existing generation strategies of landmark points face some deficiencies: the unstable results of random sampling, along with the unknown convergence time and the repeatability of data reading in k-means centers method.
24210 该文将近似奇异值分解应用于基于地标点的谱聚类，设计了一种快速地标点采样算法。 In this paper, a rapid landmark-sampling spectral clustering algorithm based on the approximate singular value decomposition is designed, which makes the sampling probability of each landmark point decided by the row norm of the approximate singular vector matrix.
24211 该算法利用由近似奇异向量矩阵行向量的长度计算的抽样概率来进行抽样，同随机抽样策略相比，保证了聚类结果的稳定性和精度，同 k 均值中心点策略相比降低了算法复杂度。 Compared with LSC algorithm based on random sampling, the clustering result of new algorithm is more stable and accurate; compared with LSC algorithm based on k-means centers, the new algorithm reduces the computational complexity.
24212 同时从理论上分析了抽样结果对原始数据的信息保持性，并对算法的性能进行了实验验证。 Moreover, the preservation of information in original data is analyzed for the landmark-sampling results theoretically. At the same time, the performance of new approach is verified by the experiments in some public data sets.
24213 为了获得精准的航空拼接图像，更好地解决图像拼接中经常出现的尺度变化、角度旋转、光照差异以及传统的 BRISK(Binary Robust Invariant Scalable Keypoints)算法匹配正确率较低，图像拼接精度低等问题，该文提出一种全新的基于有向线段的 BRISK 特征的图像拼接模型。 In order to obtain accurate aerial stitching images, this paper proposes a novel image mosaic method based on Binary Robust Invariant Scalable Keypoints (BRISK) feature of directed line segment, aiming to resolve incident scaling, rotation, changes in lighting condition, the low correct matching rate and low accuracy using conventional BRISK algorithm in image mosaic.
24214 首先，使用 BRISK 算法进行图像匹配，得到粗匹配点对，再构造有向线段及其 BRISK 特征进行邻近线段匹配，通过概率统计模型进行特征点的精匹配，最后进行加权融合和亮度均衡化进行图像融合完成图像拼接。 This method firstly uses BRISK algorithm to match in order to acquire rough point matching. Secondly, it constructs directed line segments, describes them with BRISK feature, and matches those directed segments. The method is used to purified point matching based on statistical voting. Finally, weighted fusion and luminance equalization are used to image fusion to accomplish image mosaic.