Transformer Network
Transformer networks are a class of deep learning models designed to process sequential data by leveraging self-attention mechanisms, enabling the capture of long-range dependencies within the data. Current research focuses on optimizing transformer architectures for efficiency and generalization, including exploring sparse connections, pruning techniques, and specialized hardware acceleration, as well as adapting them for diverse applications beyond natural language processing, such as image analysis, time series prediction, and signal processing. This versatility makes transformers a powerful tool across numerous scientific fields and practical applications, driving advancements in areas ranging from medical image analysis to autonomous driving and energy management.
Papers
Ice hockey player identification via transformers and weakly supervised learning
Kanav Vats, William McNally, Pascale Walters, David A. Clausi, John S. Zelek
DBIA: Data-free Backdoor Injection Attack against Transformer Networks
Peizhuo Lv, Hualong Ma, Jiachen Zhou, Ruigang Liang, Kai Chen, Shengzhi Zhang, Yunfei Yang