用于人群计数的课程学习——是否值得？
Curriculum for Crowd Counting -- Is it Worthy?
AI总结：
本文通过112组实验系统评估课程学习在人群计数中的价值，发现其能提升模型性能并加速收敛，为课程学习是否值得采用提供了实证依据。
摘要：
深度学习技术的最新进展已在若干计算机视觉问题中取得了显著性能。一种直观且引人注目的技术——课程学习（Curriculum Learning, CL）最近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了结果，但在其他任务中提升甚微或没有提升。因此，关于是否将其作为训练监督学习模型的标准方法，目前仍存在争议。在本工作中，我们使用密度估计方法研究了课程学习在人群计数中的影响。我们通过使用六种不同的课程学习设置和八种不同的人群模型，进行了112次实验，开展了详细研究。我们的实验表明，课程学习能够提升模型学习性能并缩短收敛时间。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
