论文标题
通过标签相关网格的标签分布学习
Label distribution learning via label correlation grid
论文作者
论文摘要
标签分布学习可以通过标签分布来表征实例的多义。但是，由于人工或环境因素，处理标签分布数据时，可能会引入一些噪声和不确定性。为了减轻这个问题，我们提出了一个\ textbf {l} abel \ textbf {c} orralation \ textbf {g} rid（lcg），以建模标签关系的不确定性。具体而言，我们计算训练集中标签空间的协方差矩阵，以表示标签之间的关系，然后对协方差矩阵中每个元素的信息分布（高斯分布函数）进行建模，以获得LCG。最后，我们的网络学习LCG以准确估计每个实例的标签分布。此外，我们建议在模型训练过程中提出标签分布投影算法作为正规化项。广泛的实验验证了我们方法对几个实际基准测试的有效性。
Label distribution learning can characterize the polysemy of an instance through label distributions. However, some noise and uncertainty may be introduced into the label space when processing label distribution data due to artificial or environmental factors. To alleviate this problem, we propose a \textbf{L}abel \textbf{C}orrelation \textbf{G}rid (LCG) to model the uncertainty of label relationships. Specifically, we compute a covariance matrix for the label space in the training set to represent the relationships between labels, then model the information distribution (Gaussian distribution function) for each element in the covariance matrix to obtain an LCG. Finally, our network learns the LCG to accurately estimate the label distribution for each instance. In addition, we propose a label distribution projection algorithm as a regularization term in the model training process. Extensive experiments verify the effectiveness of our method on several real benchmarks.
