Zhou Joey Tianyi, Zhang Le, Du Jiawei, Peng Xi, Fang Zhiwen, Xiao Zhe, Zhu Hongyuan
IEEE Trans Pattern Anal Mach Intell. 2022 Jul;44(7):3602-3613. doi: 10.1109/TPAMI.2021.3056518. Epub 2022 Jun 3.
Imbalanced data distribution in crowd counting datasets leads to severe under-estimation and over-estimation problems, which has been less investigated in existing works. In this paper, we tackle this challenging problem by proposing a simple but effective locality-based learning paradigm to produce generalizable features by alleviating sample bias. Our proposed method is locality-aware in two aspects. First, we introduce a locality-aware data partition (LADP) approach to group the training data into different bins via locality-sensitive hashing. As a result, a more balanced data batch is then constructed by LADP. To further reduce the training bias and enhance the collaboration with LADP, a new data augmentation method called locality-aware data augmentation (LADA) is proposed where the image patches are adaptively augmented based on the loss. The proposed method is independent of the backbone network architectures, and thus could be smoothly integrated with most existing deep crowd counting approaches in an end-to-end paradigm to boost their performance. We also demonstrate the versatility of the proposed method by applying it for adversarial defense. Extensive experiments verify the superiority of the proposed method over the state of the arts.
人群计数数据集中的数据分布不均衡会导致严重的低估和高估问题，而现有研究对此关注较少。在本文中，我们通过提出一种简单而有效的基于局部性的学习范式来解决这一具有挑战性的问题，通过减轻样本偏差来生成可泛化的特征。我们提出的方法在两个方面具有局部感知能力。首先，我们引入了一种局部感知数据划分（LADP）方法，通过局部敏感哈希将训练数据分组到不同的桶中。结果，LADP构建了一个更加平衡的数据批次。为了进一步减少训练偏差并增强与LADP的协作，我们提出了一种新的数据增强方法，称为局部感知数据增强（LADA），其中图像块根据损失进行自适应增强。所提出的方法独立于主干网络架构，因此可以在端到端范式中与大多数现有的深度人群计数方法顺利集成，以提高它们的性能。我们还通过将其应用于对抗防御来证明所提出方法的通用性。大量实验验证了所提出方法优于现有技术。
