一种用于定位部分伪造音频中篡改区域的无监督域自适应方法
An Unsupervised Domain Adaptation Method for Locating Manipulated Region in partially fake Audio
AI总结：
针对跨域部分伪造音频篡改区域定位中模型性能因域偏移下降的问题，提出基于混合专家的SDE无监督域自适应方法，通过熵筛选高信息量目标样本并生成标签融入训练，在ADD2023Track2数据集上F1达43.84%，较次优方法相对提升77.2%。
摘要：
当部分伪造音频（PFA）篡改区域定位任务涉及跨域数据集时，由于源域与目标域之间存在分布偏移，深度学习模型的性能会显著下降。为解决这一问题，现有方法通常在训练前采用数据增强策略，但它们忽略了目标域中存在而源域缺失的特征。受混合专家模型启发，我们提出了一种名为“多样性与熵样本挖掘（Samples mining with Diversity and Entropy, SDE）”的无监督方法。我们的方法首先从一组多样化的专家模型中学习，这些专家模型在源域的不同视角下均能取得优异性能，但在目标样本上存在预测歧义。我们利用这些多样化专家，通过计算样本的熵来筛选信息量最大的样本。此外，我们还针对这些筛选出的样本引入了一种标签生成方法，将其融入源域训练过程，从而整合目标域信息。我们将该方法应用于跨域部分伪造音频检测数据集ADD2023Track2。通过引入10%的目标域未知样本，我们取得了43.84%的F1分数，相比次优方法相对提升了77.2%。
英文摘要：
When the task of locating manipulation regions in partially-fake audio (PFA) involves cross-domain datasets, the performance of deep learning models drops significantly due to the shift between the source and target domains. To address this issue, existing approaches often employ data augmentation before training. However, they overlook the characteristics in target domain that are absent in source domain. Inspired by the mixture-of-experts model, we propose an unsupervised method named Samples mining with Diversity and Entropy (SDE). Our method first learns from a collection of diverse experts that achieve great performance from different perspectives in the source domain, but with ambiguity on target samples. We leverage these diverse experts to select the most informative samples by calculating their entropy. Furthermore, we introduced a label generation method tailored for these selected samples that are incorporated in the training process in source domain integrating the target domain information. We applied our method to a cross-domain partially fake audio detection dataset, ADD2023Track2. By introducing 10% of unknown samples from the target domain, we achieved an F1 score of 43.84%, which represents a relative increase of 77.2% compared to the second-best method.
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。
