AdapTiV: Sign-Similarity Based Image-Adaptive Token Merging for Vision Transformer Acceleration
Year: 2024
Type: conference-paper
Authors: Seungjae Yoo, Hangyeol Kim, Joo-Young Kim
Institution: Korea Advanced Institute of Science and Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: closed
OpenAlex ID: W4404955778