用简单损失函数提升动作分割精度，无需复杂模型。
Combining Boundary Supervision and Segment-Level Regularization for Fine-Grained Action Segmentation
- 引入边界回归与分段分布匹配双损失，仅增一个输出通道。
- 在三个数据集上提升分段一致性与边界精度，F1和编辑得分更高。
- 适合作为通用训练策略，兼容现有模型且不增加推理负担。
近期时间动作分割（TAS）研究愈发依赖复杂架构，不利于实际部署。本文提出一种轻量级双损失训练框架，仅需增加一个输出通道和两个辅助损失项，即可显著提升细粒度分割质量，对模型结构改动极小。方法结合边界回归损失（通过单通道边界预测提升定位精度）与基于累积分布函数（CDF）的分段级正则化损失（通过匹配预测与真实分段的累积分布，增强段内结构一致性）。该框架与架构无关，可作为训练时损失函数集成至现有TAS模型（如MS-TCN、C2F-TCN、FACT）中。在三个基准数据集上的实验表明，所提方法有效提升了分段一致性和边界质量，多个模型均获得更高的F1与编辑得分；而帧级准确率基本不变，说明精确分割可通过简洁的损失设计实现，无需更重的网络或推理阶段优化。
原文摘要 · Abstract (English)
Recent progress in Temporal Action Segmentation (TAS) has increasingly relied on complex architectures, which can hinder practical deployment. We present a lightweight dual-loss training framework that improves fine-grained segmentation quality with only one additional output channel and two auxiliary loss terms, requiring minimal architectural modification. Our approach combines a boundary-regression loss that promotes accurate temporal localization via a single-channel boundary prediction and a CDF-based segment-level regularization loss that encourages coherent within-segment structure by matching cumulative distributions over predicted and ground-truth segments. The framework is architecture-agnostic and can be integrated into existing TAS models (e.g., MS-TCN, C2F-TCN, FACT) as a training-time loss function. Across three benchmark datasets, the proposed method improves segment-level consistency and boundary quality, yielding higher F1 and Edit scores across three different models. Frame-wise accuracy remains largely unchanged, highlighting that precise segmentation can be achieved through simple loss design rather than heavier architectures or inference-time refinements.
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。