Human attribute analysis is a challenging task in the field of computer
vision, since the data is largely imbalance-distributed. Common techniques such
as re-sampling and cost-sensitive learning require prior-knowledge to train the
system. To address this problem, we propose a unified framework called Dynamic
Curriculum Learning (DCL) to online adaptively adjust the sampling strategy and
loss learning in single batch, which resulting in better generalization and
discrimination. Inspired by the curriculum learning, DCL consists of two level
curriculum schedulers: (1) sampling scheduler not only manages the data
distribution from imbalanced to balanced but also from easy to hard; (2) loss
scheduler controls the learning importance between classification and metric
learning loss. Learning from these two schedulers, we demonstrate our DCL
framework with the new state-of-the-art performance on the widely used face
attribute dataset CelebA and pedestrian attribute dataset RAP.

该研究提出了一种名为动态课程学习（DCL）的统一框架，可在线自适应地调整采样策略和损失学习，从而提高计算机视觉中人类属性分析任务的表现，实验结果显示 DCL 在面部属性数据集 CelebA 和行人属性数据集 RAP 上得到了新的最优性能。

不平衡数据分类的动态课程学习

Dynamic Curriculum Learning for Imbalanced Data Classification

Learning to recognize pedestrian attributes at far distance is a challenging
problem in visual surveillance since face and body close-shots are hardly
available; instead, only far-view image frames of pedestrian are given. In this
study, we present an alternative approach that exploits the context of
neighboring pedestrian images for improved attribute inference compared to the
conventional SVM-based method. In addition, we conduct extensive experiments to
evaluate the informativeness of background and foreground features for
attribute recognition. Experiments are based on our newly released pedestrian
attribute dataset, which is by far the largest and most diverse of its kind.

本文介绍了一种利用周围的行人图像 context，比传统的基于 SVM 方法更好地推断行人属性的方法，并通过我们新发布的行人属性数据集进行实验评估背景和前景特征对属性识别的相关性。