Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance

arXiv:2403.05231v1 Announce Type: new
Abstract: Motivated by the Parameter-Efficient Fine-Tuning (PEFT) in large language models, we propose LoRAT, a method that unveils the power of larger Vision Transformers (ViT) for tracking within laboratory-level resources. The essence of our work lies in adapting LoRA, a technique that fine-tunes a small subset of model parameters without adding inference latency, to the domain of visual tracking. However, unique challenges and potential domain gaps make this transfer not as easy as the first intuition. …

abstract arxiv cs.cv faster fine-tuning laboratory language language models large language large language models lies lora peft performance power resources small tracking training transformers type vision vision transformers vit work