让人体姿态模型持续学习，避免重复训练。
PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkit
- 设计持续学习框架与基准测试，模拟真实场景变化。
- 在资源受限下保持精度，验证多种正则化方法效果。
- 适合需要轻量级更新的工业部署与研究者使用。
人体姿态估计算法通常在关键点集、感知模态或部署域变化时从头训练或简单微调，效率低下且不契合实际需求。本文提出 PoseAdapt，一个开源框架与基准套件，用于持续姿态模型适应。该框架定义了领域增量和类别增量两条赛道，模拟密度、光照、模态变化及骨骼增长等现实场景。工具包支持两种流程：(i) 策略基准测试，研究人员可将持续学习（CL）方法作为插件实现，并在标准化协议下评估；(ii) 模型适应，允许从业者用少量标注数据将强预训练模型适配至新任务。我们评估了代表性正则化方法在单步与序列设置下的表现。基准要求固定轻量骨干网络、不可访问历史数据、每步预算严格，以隔离适应策略的影响，凸显在严苛资源限制下维持准确性的挑战。PoseAdapt 将现代持续学习技术与实际姿态估计需求结合，推动可随时间演进、无需重复全量重训的灵活模型发展。
原文摘要 · Abstract (English)
Human pose estimators are typically retrained from scratch or naively fine-tuned whenever keypoint sets, sensing modalities, or deployment domains change--an inefficient, compute-intensive practice that rarely matches field constraints. We present PoseAdapt, an open-source framework and benchmark suite for continual pose model adaptation. PoseAdapt defines domain-incremental and class-incremental tracks that simulate realistic changes in density, lighting, and sensing modality, as well as skeleton growth. The toolkit supports two workflows: (i) Strategy Benchmarking, which lets researchers implement continual learning (CL) methods as plugins and evaluate them under standardized protocols; and (ii) Model Adaptation, which allows practitioners to adapt strong pretrained models to new tasks with minimal supervision. We evaluate representative regularization-based methods in single-step and sequential settings. Benchmarks enforce a fixed lightweight backbone, no access to past data, and tight per-step budgets. This isolates adaptation strategy effects, highlighting the difficulty of maintaining accuracy under strict resource limits. PoseAdapt connects modern CL techniques with practical pose estimation needs, enabling adaptable models that improve over time without repeated full retraining.
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。