.png){kind=icon}
Return
SCAT: Shared-convolution adaptation tuning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.131935.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• SCAT is a novel parameter-efficient fine-tuning (PEFT) method achieving SOTA performance with minimal parameter changes. • SCAT dynamically adjusts parameter sizes, excelling in few-shot learning with limited data. • SCAT maintains efficiency, outperforming existing methods and generalizing across diverse architectures and tasks. • SCAT demonstrates superior performance on multiple benchmarks with fewer parameters.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
Cited Papers
No cited papers available