arXiv 2501.111242025-04-30cs.CV

从噪声校正的角度重新思考弱监督时序动作定位中的伪标签引导学习

Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction

Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）

Quan Zhang, Yuxin Qi, Xi Tang, Rui Yuan, Xi Lin, Ke Zhang, Chun Yuan

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对弱监督时序动作定位中伪标签噪声干扰全监督检测头学习的问题，提出两阶段噪声标签学习策略，结合帧级伪标签生成与在线修正师生框架，有效校正边界、补偿短动作并解决多对一问题，在多个基准上取得最优性能。

摘要：

伪标签学习方法已广泛应用于弱监督时序动作定位。现有工作直接利用弱监督基模型生成实例级伪标签，用于训练全监督检测头。我们认为伪标签中的噪声会干扰全监督检测头的学习，导致严重的性能损失。噪声标签的问题包括：（1）边界定位不准确；（2）未检测到短动作片段；（3）多个相邻片段被错误检测为一个片段。针对这些问题，我们引入了一种两阶段噪声标签学习策略，以利用噪声标签中的每一个潜在有用信号。首先，我们提出了一种带有上下文感知去噪算法的帧级伪标签生成模型，以细化边界。其次，我们引入了一个在线修正的师生框架，包含缺失实例补偿模块和模糊实例校正模块，以解决短动作缺失和多对一问题。此外，我们在在线修正的师生框架中应用了高质量伪标签挖掘损失，为噪声标签添加不同权重以更有效地训练。我们的模型在 THUMOS14 和 ActivityNet v1.2 基准上的检测准确率和推理速度均大幅超越了之前的最先进方法。

英文摘要：

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the fully-supervised detection head. We argue that the noise in pseudo-labels would interfere with the learning of fully-supervised detection head, leading to significant performance leakage. Issues with noisy labels include:(1) inaccurate boundary localization; (2) undetected short action clips; (3) multiple adjacent segments incorrectly detected as one segment. To target these issues, we introduce a two-stage noisy label learning strategy to harness every potential useful signal in noisy labels. First, we propose a frame-level pseudo-label generation model with a context-aware denoising algorithm to refine the boundaries. Second, we introduce an online-revised teacher-student framework with a missing instance compensation module and an ambiguous instance correction module to solve the short-action-missing and many-to-one problems. Besides, we apply a high-quality pseudo-label mining loss in our online-revised teacher-student framework to add different weights to the noisy labels to train more effectively. Our model outperforms the previous state-of-the-art method in detection accuracy and inference speed greatly upon the THUMOS14 and ActivityNet v1.2 benchmarks.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。