Cross Modality
Cross-modality research focuses on integrating information from different data types (e.g., images, text, audio) to improve model performance and understanding. Current research emphasizes developing robust methods for handling inconsistencies between modalities, particularly using techniques like contrastive learning, generative adversarial networks (GANs), and vision transformers, often within frameworks of unsupervised domain adaptation or self-training. This field is significant for advancing medical image analysis (e.g., improved segmentation and diagnosis), autonomous driving, and other applications requiring the fusion of heterogeneous data sources, ultimately leading to more accurate and reliable systems.
Papers
Reducing Domain Gap in Frequency and Spatial domain for Cross-modality Domain Adaptation on Medical Image Segmentation
Shaolei Liu, Siqi Yin, Linhao Qu, Manning Wang
An Unpaired Cross-modality Segmentation Framework Using Data Augmentation and Hybrid Convolutional Networks for Segmenting Vestibular Schwannoma and Cochlea
Yuzhou Zhuang, Hong Liu, Enmin Song, Coskun Cetinkaya, Chih-Cheng Hung