Convolution neural network is successful in pervasive vision tasks, including label distribution learning, which usually takes the form of learning an injection from the non-linear visual features to the well-defined labels. However, how the discrepancy between features is mapped to the label discrepancy is ambient, and its correctness is not guaranteed.To address these problems, we study the mathematical connection between feature and its label, presenting a general and simple framework for label distribution learning. We propose a so-called Triangular Distribution Transform (TDT) to build an injective function between feature and label, guaranteeing that any symmetric feature discrepancy linearly reflects the difference between labels. The proposed TDT can be used as a plug-in in mainstream backbone networks to address different label distribution learning tasks. Experiments on Facial Age Recognition, Illumination Chromaticity Estimation, and Aesthetics assessment show that TDT achieves on-par or better results than the prior arts.

翻译：卷积神经网络在包括标签分布学习在内的普遍视觉任务中表现出色，这类任务通常采取从非线性视觉特征到精确定义标签的注入映射形式。然而，特征差异如何映射到标签差异的机制尚不明确，且其正确性无法保证。为解决这些问题，我们研究了特征与其标签之间的数学联系，提出了一种通用且简单的标签分布学习框架。我们提出所谓的三角分布变换（TDT），在特征与标签之间构建注入函数，确保任意对称特征差异能线性反映标签间的差异。所提出的TDT可作为即插即用模块嵌入主流骨干网络，以处理不同标签分布学习任务。在人脸年龄识别、光照色度估计和美学评估等实验表明，TDT取得了与现有技术相当或更优的结果。