Recent advances in deep learning techniques have achieved remarkable performance in several computer vision problems. A notably intuitive technique called Curriculum Learning (CL) has been introduced recently for training deep learning models. Surprisingly, curriculum learning achieves significantly improved results in some tasks but marginal or no improvement in others. Hence, there is still a debate about its adoption as a standard method to train supervised learning models. In this work, we investigate the impact of curriculum learning in crowd counting using the density estimation method. We performed detailed investigations by conducting 112 experiments using six different CL settings using eight different crowd models. Our experiments show that curriculum learning improves the model learning performance and shortens the convergence time.

翻译：近期深度学习技术在多个计算机视觉问题中取得了显著性能。一种直观的技术——课程学习（Curriculum Learning, CL）被引入用于训练深度学习模型。令人惊讶的是，课程学习在某些任务中显著提升结果，但在其他任务中仅带来微小改进甚至无改进。因此，其是否应成为监督学习模型的标准训练方法仍存在争议。本研究探究了课程学习在基于密度估计方法的人群计数中的影响。我们通过使用八种不同人群模型在六种不同的CL设置下开展112项实验进行了详细调研。实验结果表明，课程学习能够提升模型学习性能并缩短收敛时间。