通过特征代理逐步对齐师生特征分布，缓解模型能力差距带来的性能下降
AgentPose: Progressive Distribution Alignment via Feature Agent for Human Pose Distillation
- 引入特征代理建模教师特征分布，实现渐进式对齐
- 在高能力差距下仍显著提升知识迁移效果
- 适合模型压缩场景中追求高精度轻量化部署的开发者
姿态蒸馏被广泛用于人体姿态估计中的模型压缩。然而，现有方法多关注教师知识的传递，常忽视师生模型间能力差距导致的性能下降问题。为此，我们提出AgentPose，一种新型姿态蒸馏方法，通过引入特征代理来建模教师特征分布，并逐步将学生特征分布与之对齐，有效缓解能力差距，增强知识迁移能力。我们在COCO数据集上进行了全面实验，验证了该方法在知识迁移上的有效性，尤其在高能力差距场景下表现突出。
原文摘要 · Abstract (English)
Pose distillation is widely adopted to reduce model size in human pose estimation. However, existing methods primarily emphasize the transfer of teacher knowledge while often neglecting the performance degradation resulted from the curse of capacity gap between teacher and student. To address this issue, we propose AgentPose, a novel pose distillation method that integrates a feature agent to model the distribution of teacher features and progressively aligns the distribution of student features with that of the teacher feature, effectively overcoming the capacity gap and enhancing the ability of knowledge transfer. Our comprehensive experiments conducted on the COCO dataset substantiate the effectiveness of our method in knowledge transfer, particularly in scenarios with a high capacity gap.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。