SoftSkip: Empowering multi-modal dynamic pruning for single-stage referring comprehension

• Main Authors: WEERAKOON, Dulanga, SUBBARAJU, Vigneshwaran, TRAN, Tuan, MISRA, Archan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Human-Robot Interaction; Referring Expression Comprehension; Pruning; Computer Vision; Natural Language Processing; Computer Engineering; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/7707; https://ink.library.smu.edu.sg/context/sis_research/article/8710/viewcontent/multimedia_final.pdf
• Institution: Singapore Management University

Supporting real-time referring expression comprehension (REC) on pervasive devices is an important capability for human-AI collaborative tasks. Model pruning techniques, applied to DNN models, can enable real-time execution even on resource-constrained devices. However, existing pruning strategies a...