Siamese Network
Siamese networks are a class of neural networks designed to learn a similarity function between pairs of inputs, primarily used for tasks like image comparison, object tracking, and similarity search. Current research focuses on enhancing Siamese network architectures, such as integrating transformers and attention mechanisms, and applying them to diverse domains including medical image analysis, remote sensing, and natural language processing. This approach offers significant advantages in scenarios with limited labeled data or a need for efficient similarity comparisons, impacting fields ranging from automated visual inspection to personalized medicine.
Papers
SAN: a robust end-to-end ASR model architecture
Zeping Min, Qian Ge, Guanhua Huang
A few-shot learning approach with domain adaptation for personalized real-life stress detection in close relationships
Kexin Feng, Jacqueline B. Duong, Kayla E. Carta, Sierra Walters, Gayla Margolin, Adela C. Timmons, Theodora Chaspari