SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning
Zhenglun Kong, Peiyan Dong, Xiaolong Ma, Xin Meng, Wei Niu, Mengshu Sun, Xuan Shen, Geng Yuan, Bin Ren, Hao Tang, Minghai Qin, Yanzhi Wang
Topics & Concepts
Computer scienceSecurity tokenLatency (audio)ComputationMobile deviceTransformerComputer hardwareEmbedded systemComputer engineeringComputer networkAlgorithmOperating systemQuantum mechanicsPhysicsTelecommunicationsVoltageAdvanced Neural Network ApplicationsCCD and CMOS Imaging SensorsAdvanced Image and Video Retrieval Techniques