arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.05901cs.AI
收藏

通过优势加权排序揭示二元抑郁检测中的潜在抑郁严重程度

Uncovering Latent Depression Severity for Binary Depression Detection via Advantage-weighting Ranking

South China Normal University(华南师范大学)

Manning Gao, Tingyi Liu, Leheng Zhang, Haifeng Hu, Yuncheng Jiang, Sijie Mai

AI总结:

研究利用视听数据检测抑郁的挑战,提出含时间编码器和相互变压器的多模态框架,核心是二元优势加权排序损失,通过两种机制优化潜在空间分布,实验表明该模型重建潜在有序结构,性能达最优。

摘要:

使用视听数据进行自动抑郁检测面临重大挑战,特别是在解开重叠特征分布和建立稳健决策边界方面。为解决此问题,我们提出了一个细粒度多模态框架,具有时间编码器和相互变压器以促进深度跨模态融合。我们的核心贡献是二元优势加权排序损失,它通过两个互补机制优化潜在空间分布:优势加权分离,通过计算成对预测差异矩阵挖掘硬对并根据其难度动态加权;优势加权紧凑性,最小化类内方差以迫使特征围绕各自类中心聚类。在D-vlog和LMVD上的大量实验表明,我们的模型通过对硬对进行优先级排序来重建潜在的有序结构,从而实现了最新的性能。

英文摘要:

Automatic depression detection using audio-visual data faces significant challenges, particularly in disentangling overlapping feature distributions and establishing robust decision boundaries. To address this, we propose a fine-grained multimodal framework featuring a temporal encoder and a mutual transformer to facilitate deep cross-modal fusion. Our core contribution is the Binary Advantage-weighting Ranking Loss, which optimizes the latent space distribution through two complementary mechanisms: Advantage-weighted Separation, which mines hard pairs by computing a pairwise prediction difference matrix and dynamically weighting them based on their difficulty; and Advantage-weighted Compactness, which minimizes intra-class variance to force features to cluster around their respective class centers. Extensive experiments on D-vlog and LMVD demonstrate that our model reconstructs the latent ordinal structure by prioritizing hard pairs, thereby achieving state-of-the-art performance.

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。

↑