This paper systematically sorts out the technical connotation and typical cases of lightweight models, and analyzes their application practices in the fields of medical image analysis, financial real-time risk control, and predictive maintenance of industrial Internet of Things.
Experiments on various edge devices and DNN models, including CNN-based and transformer-based workloads, show that ProfEdge reduces profiling errors by up to 80% and saves over 70% of profiling construction cost compared with existing methods.
Wei-Long Wang, Song-Tao Lu, Jia-Wei Liu et al.· ACM Transactions on Internet...· 0 citations
Findings confirm that combining complementary compression strategies yields substantially better performance-efficiency trade-offs than any single technique applied in isolation.
Upma Sharma Archana· International Journal of Res...· 0 citations
Despite the remarkable achievements of deep neural networks (DNNs) in numerous fields, the growing number of parameters and computational complexity severely limit their deployment feasibility on edge devices. Against this backdrop, lightweight DNNs have not only become a hot topic in academic research but also a key t...
The conflicting requirements of high diagnostic accuracy and limited computational resources pose a big challenge in real-time detection of disease, especially for resource constrained healthcare devices. We suggest a thin-edge AI solution that allows an efficient prediction of the disease in a certain device located a...
Amitava Biswas· Journal of Machine Learning...· 0 citations
This work surveys dozens of recent works that report compression results on real hardware and extracts practical deployment guidelines from them, and deploys compact language and image models on GPU, CPU, and Raspberry Pi platforms across question answering and image segmentation.
Subhransu Das, Jiaming Cheng, Arnav Kumar et al.· 0 citations
Medical vision foundation models pretrained on large-scale domain-specific data achieve strong clinical performance, but their computational cost precludes deployment on resource-constrained edge devices. We investigate whether the domain-specific representations of a medical foundation model transfer more effectively...
Shu-Wei Liu· Informatica· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
