From One to Many: Portable Model Construction With Independent Network Units

Artificial Intelligence of Things (AIoT) devices are highly versatile, operating in diverse environments, which necessitates local fine-tuning of deployed models to ensure compatibility with specific conditions. However, traditional fine-tuning methods often rely on cloud-based collaborative training, which is impractical for complete on-device deployment and incurs high retuning costs when the environment changes. To address these challenges, we propose a portable and modular approach named portable model construction with independent network units (POINT), which enables efficient customization for diverse tasks on the AIoT devices. POINT combines cloud-based model management with feature reuse to efficiently adapt pretrained models using minimal local data. This enables offline fine-tuning directly on end-side devices without relying on extensive computational resources. Compared to parameter-efficient fine-tuning (PEFT) approaches like low-rank adaptation (LoRA), POINT reduces the number of trainable parameters by up to 98.94%. During deployment, task-relevant models are selected from a centralized cloud repository and integrated as the backbone of the target model. Only a lightweight task-specific head is trained for downstream tasks, making POINT exceptionally lightweight and suitable for end-side customization. To mitigate performance degradation as the number of selected models increases, POINT incorporates a dynamic optimization strategy, which balances resource constraints and model performance by adaptively managing the learning process. Extensive experiments demonstrate that POINT achieves competitive results with only 100 images per category and 20 epochs of training, significantly reducing computational and resource requirements. Compared to traditional methods, POINT offers an efficient, scalable, and resource-conscious solution for deploying AI models in diverse and constrained AIoT environments.