MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge

Excerpt

arXiv:2610.08669v1 Announce Type: new Abstract: On-device learning is necessary when the model encounters user-,sensor-, or environment-specific shifts after deployment. Although parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA) variants, enable efficient adaptation at the edge, the limiting resource for Convolutional Neural Network (CNN) adaptation is often not the number of trainable parameters but the activation state that must be retained until the backw