Paper Contents
Abstract
The proliferation of mobile and edge devices necessitates the development of efficient deep learning models capable of on-device image recognition under resource constraints. This article reviews current advancements in lightweight architectures, optimization techniques, and application-specific solutions. The review identifies key trends, challenges, and future directions in developing models that balance accuracy and efficiency in constrained environments, emphasizing both theoretical advancements and practical implementations. Additionally, the article explores emerging trends in hardware-software co-design and adaptive model scaling to meet the evolving demands of diverse application domains.
Copyright
Copyright © 2025 Dhanshwar Suryavanshi1. This is an open access article distributed under the Creative Commons Attribution License.
