用自适应课程学习提升视频域迁移效果，解决伪标签噪声问题。
Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation
- 通过双向预测对齐评估可靠性，动态调整样本权重。
- 在多个数据集上优于当前最优方法，显著降低过拟合风险。
- 适合需要高鲁棒性视频域适应的场景，如跨域视频分析。
近期的无源无监督视频域适应方法利用视觉-语言模型生成伪标签，但受伪标签噪声和预测过度自信的影响，泛化能力受限。本文提出 Co-STAR 框架，结合课程学习与源训练教师模型和对比视觉-语言模型（CLIP）间的协同自训练。其课程学习采用基于可靠性的权重函数，衡量教师与 CLIP 之间的双向预测对齐度，在保持困难样本不确定性的同时，优先选择两者预测高度一致时的可靠伪标签。为进一步提升适应性能，提出自适应课程正则化，根据置信度与预测稳定性概率性地调整样本学习优先级，缓解对噪声和过度自信样本的过拟合。在多个视频域适应基准上的实验表明，Co-STAR 持续超越现有先进方法。代码已公开：https://github.com/Plrbear/Co-Star
原文摘要 · Abstract (English)
Recent advances in Source-Free Unsupervised Video Domain Adaptation (SFUVDA) leverage vision-language models to enhance pseudo-label generation. However, challenges such as noisy pseudo-labels and over-confident predictions limit their effectiveness in adapting well across domains. We propose Co-STAR, a novel framework that integrates curriculum learning with collaborative self-training between a source-trained teacher and a contrastive vision-language model (CLIP). Our curriculum learning approach employs a reliability-based weight function that measures bidirectional prediction alignment between the teacher and CLIP, balancing between confident and uncertain predictions. This function preserves uncertainty for difficult samples, while prioritizing reliable pseudo-labels when the predictions from both models closely align. To further improve adaptation, we propose Adaptive Curriculum Regularization, which modifies the learning priority of samples in a probabilistic, adaptive manner based on their confidence scores and prediction stability, mitigating overfitting to noisy and over-confident samples. Extensive experiments across multiple video domain adaptation benchmarks demonstrate that Co-STAR consistently outperforms state-of-the-art SFUVDA methods. Code is available at: https://github.com/Plrbear/Co-Star
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。