Adaptive class token knowledge distillation for efficient vision transformer

Minchan Kang; Sanghyeok Son; Dae‐Shik Kim

doi:10.1016/j.knosys.2024.112531

ScienceGate Book Chapters

JOURNAL ARTICLE

Adaptive class token knowledge distillation for efficient vision transformer

Minchan Kang Sanghyeok Son Dae‐Shik Kim

Year: 2024 Journal: Knowledge-Based Systems Vol: 304 Pages: 112531-112531 Publisher: Elsevier BV

DOI: 10.1016/j.knosys.2024.112531

Get Full-Text PDF Get Analytical Report

Keywords:

Transformer Distillation Security token Computer science Class (philosophy) Artificial intelligence Engineering Electrical engineering Computer network Chemistry Voltage Chromatography

Metrics

Cited By

2.56

FWCI (Field Weighted Citation Impact)

Refs

0.86

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Machine Learning and ELM

Physical Sciences → Computer Science → Artificial Intelligence

Advanced Memory and Neural Computing

Physical Sciences → Engineering → Electrical and Electronic Engineering

Brain Tumor Detection and Classification

Life Sciences → Neuroscience → Neurology

Adaptive class token knowledge distillation for efficient vision transformer

Metrics

Citation History

Topics

Related Documents

AToM: Adaptive Token Merging for Efficient Acceleration of Vision Transformer

Adaptive Token Pruning for Vision Transformer

Efficient Vision Transformer via Token Merger

FedDiT: Federated Learning by Distillation Token Enhanced Vision Transformer

Efficient Vision Transformer Deployment on Google Coral Through Knowledge Distillation