发表机构
Kunming University of Science and Technology; Tianjin University; University of New South Wales; Tianjin University of Sport; Southeast University; Hebei University of Technology（昆明理工大学; 天津大学; 新南威尔士大学; 天津体育学院; 东南大学; 河北工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对跨任务学习中粒度不匹配导致的干扰问题，提出跨粒度社会化协作框架，通过渐进式自适应层次交互调控信息交换，在无人机检测与分割基准上验证了性能提升。
AI 中文摘要
跨异构任务的联合学习通常被视为通过特征共享、蒸馏或辅助监督实现的任务耦合。然而，在跨任务学习中，表征粒度和监督粒度的不匹配使得这种耦合容易产生干扰、教师偏差或单向坍缩。我们认为，跨粒度学习本质上是一个层次化交互调控问题，而非简单的任务耦合。这一问题在无人机感知中尤为突出，因为视觉偏移和检测-分割目标天然形成粗粒度和细粒度的知识源。为系统研究该问题，我们引入了CrossUAV，一个用于联合目标检测和实例分割的无人机基准，为跨粒度任务协作提供统一评估平台。为应对这些挑战，我们提出了跨粒度社会化协作（CGSC），一种渐进式自适应框架，用于调控任务在网络层次间交换信息的时机、位置和方式。CGSC逐步激活跨任务交互，并根据任务贡献自适应调整强度，在抑制有害干扰的同时利用互补的粗粒度和细粒度结构。大量实验表明，该方法在两个任务上均取得了一致的性能提升，验证了层次化动态交互作为跨粒度协作的有效机制。
英文摘要
Joint learning across heterogeneous tasks is often treated as task coupling through feature sharing, distillation, or auxiliary supervision. However, in cross-task learning, mismatched representational and supervisory granularities make such coupling prone to interference, teacher bias, or unidirectional collapse. We argue that cross-granularity learning is fundamentally a problem of hierarchical interaction regulation rather than simple task coupling. This issue is particularly evident in UAV perception, where visual shifts and detection--segmentation objectives naturally form coarse- and fine-grained knowledge sources. To systematically study this problem, we introduce CrossUAV, a UAV benchmark for joint object detection and instance segmentation that provides a unified evaluation platform for cross-granularity task collaboration. To address these challenges, we propose Cross-Granularity Socialized Collaboration (CGSC), a progressive and adaptive framework that regulates when, where, and how tasks exchange information across network hierarchies. CGSC progressively activates cross-task interactions and adaptively adjusts the strength according to task contribution, suppressing harmful interference while exploiting complementary coarse- and fine-grained structures. Extensive experiments demonstrate consistent improvements on both tasks, validating hierarchical dynamic interaction as an effective mechanism for cross-granularity collaboration.
Comments9 pages, 6 figures
