Enhancing multimodal depression detection with intra- and inter-sample contrastive learning

Meiling Li, Yuting Wei, Yangfu Zhu, Siqi Wei, Bin Wu

Abstract: Highlights•We propose IISFD, which provides a novel perspective for introducing additional inter- and intra-class supervisory signals in depression detection.•We utilize a multimodal fusion module to integrate multiple modalities and extract the most significant multimodal information from the samples.•Experiments on public datasets demonstrate that our model outperforms state-of-the-art methods, highlighting the effectiveness of IISFD.