Audio-Visual Source Localization (AVSL) aims to locate sounding objects
within video frames given the paired audio clips. Existing methods
predominantly rely on self-supervised contrastive learning of audio-visual
correspondence. Without any bounding-box annotations, they struggle to achieve
precise localization, especially for small objects, and suffer from blurry
boundaries and false positives. Moreover, the naive semi-supervised method is
poor in fully leveraging the information of abundant unlabeled data. In this
paper, we propose a novel semi-supervised learning framework for AVSL, namely
Dual Mean-Teacher (DMT), comprising two teacher-student structures to
circumvent the confirmation bias issue. Specifically, two teachers, pre-trained
on limited labeled data, are employed to filter out noisy samples via the
consensus between their predictions, and then generate high-quality
pseudo-labels by intersecting their confidence maps. The sufficient utilization
of both labeled and unlabeled data and the proposed unbiased framework enable
DMT to outperform current state-of-the-art methods by a large margin, with CIoU
of 90.4% and 48.8% on Flickr-SoundNet and VGG-Sound Source, obtaining 8.9%,
9.6% and 4.6%, 6.4% improvements over self- and semi-supervised methods
respectively, given only 3% positional-annotations. We also extend our
framework to some existing AVSL methods and consistently boost their
performance.

提出一种新的半监督学习框架，称为 Dual Mean-Teacher（DMT），通过两个教师 - 学生结构绕过确认偏差问题，充分利用有标签和无标签数据，通过教师之间的一致性过滤噪声样本并生成高质量的伪标签，从而在 Audio-Visual Source Localization（AVSL）中取得了明显优于当前先进方法的性能。