论文标题
通过课程预培训来计算严重压缩的图像的人群
Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training
论文作者
论文摘要
JPEG图像压缩算法是一种广泛使用的技术，用于降低边缘和云计算设置。但是，在深层神经网络处理的图像上应用这种有损压缩会导致明显的准确性降解。受课程学习范式的启发，我们提出了一种称为课程预训练（CPT）的培训方法，用于人群计数压缩图像，从而减轻了由于有损压缩而导致的准确性下降。我们通过对三个人群计数数据集的大量实验，两个人群计数DNN模型和各种压缩级别来验证方法的有效性。所提出的训练方法对超参数并不过于敏感，并减少了误差，尤其是对于重压图像，最多可达19.70％。
JPEG image compression algorithm is a widely used technique for image size reduction in edge and cloud computing settings. However, applying such lossy compression on images processed by deep neural networks can lead to significant accuracy degradation. Inspired by the curriculum learning paradigm, we propose a training approach called curriculum pre-training (CPT) for crowd counting on compressed images, which alleviates the drop in accuracy resulting from lossy compression. We verify the effectiveness of our approach by extensive experiments on three crowd counting datasets, two crowd counting DNN models and various levels of compression. The proposed training method is not overly sensitive to hyper-parameters, and reduces the error, particularly for heavily compressed images, by up to 19.70%.
