MoPEFT: A Mixture-of-PEFTs for the Segment Anything Model

Autor:	Sahay, Rajat, Savakis, Andreas
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	The emergence of foundation models, such as the Segment Anything Model (SAM), has sparked interest in Parameter-Efficient Fine-Tuning (PEFT) methods that tailor these large models to application domains outside their training data. However, different PEFT techniques modify the representation of a model differently, making it a non-trivial task to select the most appropriate method for the domain of interest. We propose a new framework, Mixture-of-PEFTs methods (MoPEFT), that is inspired by traditional Mixture-of-Experts (MoE) methodologies and is utilized for fine-tuning SAM. Our MoPEFT framework incorporates three different PEFT techniques as submodules and dynamically learns to activate the ones that are best suited for a given data-task setup. We test our method on the Segment Anything Model and show that MoPEFT consistently outperforms other fine-tuning methods on the MESS benchmark. Comment: Workshop on Foundation Models, CVPR 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2405.00293 Zobrazit plný text záznamu View this record from Arxiv