Label Noise Robust Crowd Counting with Loss Filtering Factor

Crowd counting, a crucial computer vision task, aims at estimating the number of individuals in various environments. Each person in crowd counting datasets is typically annotated by a point at the center of the head. However, challenges like dense crowds, diverse scenarios, significant obscuration, and low resolution lead to inevitable label noise, adversely impacting model performance. Driven by the need to enhance model robustness in noisy environments and improve accuracy, we propose the Loss Filtering Factor (LFF) and the corresponding Label Noise Robust Crowd Counting (LNRCC) training scheme. LFF innovatively filters out losses caused by label noise during training, enabling models to focus on accurate data, thereby increasing reliability. Our extensive experiments demonstrate the effectiveness of LNRCC, which consistently improves performance across all models and datasets, with an average enhancement of 3.68% in Mean Absolute Error (MAE), 6.7% in Mean Squared Error (MSE) and 4.68% in Grid Average Mean Absolute Error (GAME). The universal applicability of this approach, coupled with its ease of integration into any neural network model architecture, marks a significant advancement in the field of computer vision, particularly in addressing the pivotal issue of accuracy in crowd counting under challenging conditions.

人群计数是一项至关重要的计算机视觉任务，旨在估算不同场景下的人群个体总数。人群计数数据集中的每个个体通常以头部中心点作为标注点。然而，人群密集、场景多样、严重遮挡以及分辨率低下等诸多挑战会导致不可避免的标签噪声问题，进而对模型性能产生负面影响。为提升模型在噪声环境下的鲁棒性并改善计数精度，本文提出了损失过滤因子（Loss Filtering Factor，LFF）以及对应的标签噪声鲁棒人群计数（Label Noise Robust Crowd Counting，LNRCC）训练方案。LFF可在训练过程中创新性地滤除由标签噪声引发的损失项，使模型能够聚焦于有效准确的样本数据，进而提升模型可靠性。我们开展的大量实验验证了LNRCC的有效性：该方案在所有模型与数据集上均能持续提升性能，平均使平均绝对误差（Mean Absolute Error，MAE）降低3.68%，均方误差（Mean Squared Error，MSE）降低6.7%，并使网格平均绝对误差（Grid Average Mean Absolute Error，GAME）降低4.68%。该方案具备广泛的通用性，且可轻松集成至任意神经网络模型架构中，这标志着计算机视觉领域取得了重要进展，尤其在应对复杂场景下人群计数的核心精度问题上具有重大意义。