通过点标注概率图容忍密集目标计数中的标注偏移
Tolerating Annotation Displacement in Dense Object Counting via Point Annotation Probability Map
AI总结：
针对密集目标计数中人工标注导致的标注偏移问题，提出基于广义高斯分布的点标注概率图PAPM，含手工设计与自适应学习两种方法，可集成至其他模型提升鲁棒性，实验验证了其有效性。
摘要：
拥挤场景下的目标计数仍是计算机视觉领域的一项挑战。当前基于深度学习的方法通常将其建模为高斯密度回归问题。这种暴力回归方法虽然有效，但可能未妥善考虑人工标注过程中产生的标注偏移问题，而标注偏移可能导致分布差异。我们推测，在密集目标计数任务中考虑标注偏移是有益的。为获得对标注偏移的强鲁棒性，本文利用带宽和形状参数可调的广义高斯分布（GGD）函数构建学习目标点标注概率图PAPM。具体而言，我们首先提出一种手工设计的PAPM方法（HD-PAPM），其中设计了基于GGD的函数以容忍标注偏移。对于端到端训练，手工设计的PAPM可能并非特定网络和数据集的最优选择，因此提出了自适应学习的PAPM方法（AL-PAPM）。为提升对标注偏移的鲁棒性，我们设计了一种基于GGD的有效传输代价函数。所提出的PAPM可与其他方法集成，我们还通过修改匹配代价矩阵将PAPM与P2PNet结合，形成P2P-PAPM，这也能提升P2PNet对标注偏移的鲁棒性。大量实验证明了所提方法的优越性。
英文摘要：
Counting objects in crowded scenes remains a challenge to computer vision. The current deep learning based approach often formulate it as a Gaussian density regression problem. Such a brute-force regression, though effective, may not consider the annotation displacement properly which arises from the human annotation process and may lead to different distributions. We conjecture that it would be beneficial to consider the annotation displacement in the dense object counting task. To obtain strong robustness against annotation displacement, generalized Gaussian distribution (GGD) function with a tunable bandwidth and shape parameter is exploited to form the learning target point annotation probability map, PAPM. Specifically, we first present a hand-designed PAPM method (HD-PAPM), in which we design a function based on GGD to tolerate the annotation displacement. For end-to-end training, the hand-designed PAPM may not be optimal for the particular network and dataset. An adaptively learned PAPM method (AL-PAPM) is proposed. To improve the robustness to annotation displacement, we design an effective transport cost function based on GGD. The proposed PAPM is capable of integration with other methods. We also combine PAPM with P2PNet through modifying the matching cost matrix, forming P2P-PAPM. This could also improve the robustness to annotation displacement of P2PNet. Extensive experiments show the superiority of our proposed methods.
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。
