Search Results for author:
Found 5 papers, 3 papers with code
Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach
Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters.
Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing
Consequently, effectively adapting large pre-trained models to downstream tasks in an efficient manner has become a prominent research area.
Self-Supervised Node Representation Learning via Node-to-Neighbourhood Alignment
Considering the excessive memory overheads of contrastive learning, we further propose a negative-free solution, where the main contribution is a Graph Signal Decorrelation (GSD) constraint to avoid representation collapse and over-smoothing.
Learning Pixel-Adaptive Weights for Portrait Photo Retouching
Secondly, as neighboring pixels exhibit different affinities to the center pixel, we estimate a local attention mask to modulate the influence of neighboring pixels.
Sphingolipid biosynthesis modulates plasmodesmal ultrastructure and phloem unloading
During phloem unloading, multiple cell-to-cell transport events move organic substances to the root meristem.
