发表机构
University of Arkansas（阿肯色大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出DualCount，一种实例感知双解码器框架，通过密度与点结构耦合及几何约束，在零样本计数中减少误差并达到新最优。
AI 中文摘要
零样本目标计数旨在估计由文本查询指定的目标数量，而无需类别特定的训练。近期方法主要依赖于密度回归或检测式实例预测。尽管有效，基于密度的模型常因质量分配约束不足而遭受空间模糊和背景泄漏，导致在复杂场景中产生碎片化或偏重局部的表示，从而增加计数误差。在本工作中，我们提出了一种实例感知的双解码器框架，该框架在结构上将密度表示与点表示耦合用于零样本目标计数。我们不再将密度估计视为独立的逐像素回归，而是将其解释为在潜在目标实例集合上的结构化质量分配问题。预测的实例中心引出了密度图的软实例级分解，在此基础上我们施加两个几何约束：（1）每个实例的质量守恒，确保每个目标贡献约一个单位的密度质量；（2）质心对齐，鼓励每个密度分量围绕其对应的预测中心集中。这些约束引入了实例级的几何一致性，并带来更准确的质量分配，从而减少计数误差。在FSC-147、PUCPR+和CARPK上的大量实验表明，我们的方法持续减少计数误差，并在零样本目标计数中确立了新的最先进性能。
英文摘要
Zero-shot object counting aims to estimate the number of objects specified by a text query without category-specific training. Recent approaches primarily rely on density regression or detection-style instance prediction. While effective, density-based models often suffer from spatial ambiguity and background leakage due to weakly regulated mass allocation, leading to fragmented or part-biased representations that increase counting error in complex scenes. In this work, we propose an instance-aware dual-decoder framework that structurally couples density and point representations for zero-shot object counting. Instead of treating density estimation as independent pixel-wise regression, we interpret it as a structured mass allocation problem over a latent set of object instances. Predicted instance centers induce a soft instance-wise decomposition of the density map, upon which we enforce two geometric constraints: (1) per-instance mass conservation, ensuring each object contributes approximately one unit of density mass, and (2) center-of-mass alignment, encouraging each density component to concentrate around its corresponding predicted center. These constraints introduce instance-level geometric consistency and lead to more accurate mass allocation, thereby reducing counting error. Extensive experiments on FSC-147, PUCPR+, and CARPK show that our approach consistently reduces counting error and establishes new state-of-the-art performance in zero-shot object counting.
CommentsECCV 2026
