期刊
IEEE TRANSACTIONS ON CYBERNETICS
卷 52, 期 6, 页码 4675-4687出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2020.3033428
关键词
Training; Decoding; Feature extraction; Estimation; Standards; Neural networks; Task analysis; Crowd counting; curriculum learning (CL); neural network
类别
资金
- National Natural Science Foundation of China [U1864204, 61773316, U1801262, 61871470]
This article proposes a lightweight model and a density-aware curriculum learning training strategy for crowd counting. The experimental results demonstrate outstanding performance and effectiveness of these methods.
Recently, crowd counting draws much attention on account of its significant meaning in congestion control, public safety, and ecological surveys. Although the performance is improved dramatically due to the development of deep learning, the scales of these networks also become larger and more complex. Moreover, a large model also entails more time to train for better performance. To tackle these problems, this article first constructs a lightweight model, which is composed of an image feature encoder and a simple but effective decoder, called the pixel shuffle decoder (PSD). PSD ends with a pixel shuffle operator, which can display more density information without increasing the number of convolutional layers. Second, a density-aware curriculum learning (DCL) training strategy is designed to fully tap the potential of crowd counting models. DCL gives each predicted pixel a weight to determine its predicting difficulty and provides guidance on obtaining better generalization. Experimental results exhibit that PSD can achieve outstanding performance on most mainstream datasets while training under the DCL training framework. Besides, we also conduct some experiments about adopting DCL on existing typical crowd counters, and the results show that they all obtain new better performance than before, which further validates the effectiveness of our method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据