Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning
Instruction tuning of Large Vision-language Models (LVLMs) has revolutionized the development of versatile models with zero-shot generalization across a wide range of downstream vision-language tasks. However, the diversity of training tasks of different sources and formats would lead to inevitable task conflicts, where different tasks conflict for the same set of model parameters, resulting in sub-optimal instruction-following abilities. To address that, we propose the Mixture of Cluster-conditional LoRA Experts (MoCLE), a novel Mixture of Experts (MoE) architecture designed to activate the task-customized model parameters based on the instruction clusters. A separate universal expert is further incorporated to improve generalization capabilities of MoCLE for novel instructions. Extensive experiments on InstructBLIP and LLaVA demonstrate the effectiveness of MoCLE.
PDF Abstract
Visual Question Answering
Flickr30k
GQA
TextVQA
OK-VQA
ScienceQA
Hateful Memes
A-OKVQA
VQA-RAD
PathVQA
VSR
SLAKE
IconQA
GeoQA
iVQA
