5 citations · 5 across the 3 of their papers we have counts for
4 papers
Beyond Low-Rank Parameterization: Narrowing the Gap Between LoRA and Full Fine-Tuning via Gradient Decomposition
Yihao Ouyang, Shiwei Li, Haozhao Wang +5
Low-Rank Adaptation (LoRA) is a widely used approach to parameter-efficient fine-tuning (PEFT), yet a performance gap can remain relative to full fine-tuning (FFT). Many LoRA varia…
Nonlinearity as Rank: Generative Low-Rank Adapter with Radial Basis Functions
Yihao Ouyang, Shiwei Li, Haozhao Wang +7
Low-rank adaptation (LoRA) approximates the update of a pretrained weight matrix using the product of two low-rank matrices. However, standard LoRA follows an explicit-rank paradig…
A Novel Hybrid Approach for Retinal Vessel Segmentation with Dynamic Long-Range Dependency and Multi-Scale Retinal Edge Fusion Enhancement
Yihao Ouyang, Xunheng Kuang, Mengjia Xiong +2
Accurate retinal vessel segmentation provides essential structural information for ophthalmic image analysis. However, existing methods struggle with challenges such as multi-scale…
Adaptive Perception Transformer for Temporal Action Localization
Yizheng Ouyang, Tianjin Zhang, Weibo Gu +1
Temporal action localization aims to predict the boundary and category of each action instance in untrimmed long videos. Most of previous methods based on anchors or proposals negl…