Convolutional Neural Networks (ConvNets) have achieved excellent recognition
performance in various visual recognition tasks. A large labeled training set
is one of the most important factors for its success. However, it is difficult
to collect sufficient training images with precise labels in some domains such
as apparent age estimation, head pose estimation, multi-label classification
and semantic segmentation. Fortunately, there is ambiguous information among
labels, which makes these tasks different from traditional classification.
Based on this observation, we convert the label of each image into a discrete
label distribution, and learn the label distribution by minimizing a
Kullback-Leibler divergence between the predicted and ground-truth label
distributions using deep ConvNets. The proposed DLDL (Deep Label Distribution
Learning) method effectively utilizes the label ambiguity in both feature
learning and classifier learning, which help prevent the network from
over-fitting even when the training set is small. Experimental results show
that the proposed approach produces significantly better results than
state-of-the-art methods for age estimation and head pose estimation. At the
same time, it also improves recognition performance for multi-label
classification and semantic segmentation tasks.

该论文提出一种名为 DLDL（Deep Label Distribution Learning）的方法，通过最小化深度 ConvNets 预测和 ground-truth 标签分布之间的 Kullback-Leibler 散度来学习标签分布，有效地利用标签模糊性，并在训练集较小的情况下防止网络过度拟合，显著提高了年龄估计和头部姿态估计的结果，同时还改进了多标签分类和语义分割任务的识别性能。