Angular Visual Hardness
Angular Visual Hardness
复制标题
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
高斯模拟图：我们从两个多变量正态分布（每个1000）生成2000 3-D随机向量，并归一化为单位标准，在图7中的左图中以红色和绿色为单位。输入一个简单的多层感知到一个3⇥2的隐藏层，我们计算每个数据点的AVH分数。得分很明显，位于两个簇的交点上的AVH得分是较高的，这与我们还可以计算出右图所示的特征嵌入的直觉请参阅视觉上的硬示例没有明显的相关性。
Gaussian Simulation Plot: We generate 2000 3-d random vectors from two multivariate normal distribution (1000 for each) and normalize to unit norm, shown in red and green color on the left plot in figure 7. Then these data points are passed as the inputs to a simple multi layer perceptron classification model with one 3⇥ 2 hidden layer. Upon convergence, we compute the AVH scores for each data point. The middle image shows the visualization of AVH scores for all data points, with lighter color representing higher AVH scores. It is obvious that AVH scores for points lying on the intersection of two clusters are higher, which agrees with the intuition that those are hard examples. We also compute the `2 norm of the feature embeddings shown in the right plot. One can see there is no obvious correlation with visually hard examples.