Audio-Visual Source Localization (AVSL) is the task of identifying specific
sounding objects in the scene given audio cues. In our work, we focus on
semi-supervised AVSL with pseudo-labeling. To address the issues with vanilla
hard pseudo-labels including bias accumulation, noise sensitivity, and
instability, we propose a novel method named Cross Pseudo-Labeling (XPL),
wherein two models learn from each other with the cross-refine mechanism to
avoid bias accumulation. We equip XPL with two effective components. Firstly,
the soft pseudo-labels with sharpening and pseudo-label exponential moving
average mechanisms enable models to achieve gradual self-improvement and ensure
stable training. Secondly, the curriculum data selection module adaptively
selects pseudo-labels with high quality during training to mitigate potential
bias. Experimental results demonstrate that XPL significantly outperforms
existing methods, achieving state-of-the-art performance while effectively
mitigating confirmation bias and ensuring training stability.

我们的研究聚焦于半监督 AVSL 中的伪标签方法，提出了一种名为 Cross Pseudo-Labeling（XPL）的新方法，通过交互学习和交叉精炼机制，避免偏见积累，并结合软伪标签和课程数据选择模块以实现稳定训练，实验证明 XPL 相较于现有方法在性能上显著优越，并在保持稳定性的同时有效减轻了确认偏见。