Skip to content
Research

COLORA: Efficient Fine-Tuning for Convolutional Models with a Study Case on Optical Coherence Tomography Image Classification.

arXiv:2505.18315v5 Announce Type: replace-cross Abstract: We introduce CoLoRA (Convolutional Low-Rank Adaptation), a parameter-efficient fine-tuning method for convolutional neural networks (CNNs). CoLoRA extends LoRA to convolutional layers by decomposing ker

arXiv cs.AIResearch source·