用可逆图卷积网络减少标注需求，高效识别骨骼动作
Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networks
- 设计新评分函数，自动选最有价值的样本标注
- 在两个数据集上仅用少量标注即超越现有方法
- 适合标注资源稀缺的动作识别任务
基于骨骼的动作识别是图像处理领域的热点。该任务的关键挑战在于依赖大规模人工标注数据集，而数据收集成本高、耗时长。本文提出一种新型标签高效的方法，利用图卷积网络（GCNs）进行骨骼动作识别。核心贡献在于设计了一种新的获取函数，通过优化数据代表性、多样性与不确定性混合目标，选择最具信息量的样本子集进行标注。同时，通过引入可逆图卷积网络，将数据从原始空间映射到潜在空间，更易捕捉数据内在分布。在两个具有挑战性的骨骼动作识别数据集上进行的大量实验表明，所提方法在标签使用极少的情况下仍显著优于现有工作。
原文摘要 · Abstract (English)
Skeleton-based action recognition is a hotspot in image processing. A key challenge of this task lies in its dependence on large, manually labeled datasets whose acquisition is costly and time-consuming. This paper devises a novel, label-efficient method for skeleton-based action recognition using graph convolutional networks (GCNs). The contribution of the proposed method resides in learning a novel acquisition function -- scoring the most informative subsets for labeling -- as the optimum of an objective function mixing data representativity, diversity and uncertainty. We also extend this approach by learning the most informative subsets using an invertible GCN which allows mapping data from ambient to latent spaces where the inherent distribution of the data is more easily captured. Extensive experiments, conducted on two challenging skeleton-based recognition datasets, show the effectiveness and the outperformance of our label-frugal GCNs against the related work.
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。