Adaptive EfficientNet: Dynamic Compound Scaling for Resource-Optimal Deep Learning Article Swipe

MAKE IMPACT

Revista, Zen , IA, 10 · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.5281/zenodo.17822377

The widespread adoption of deep learning models in diverse applications often clashes with the stringent resource constraints of deployment environments, particularly for mobile and edge devices. Traditional deep neural networks, while achieving remarkable accuracy, typically demand significant computational power, memory, and energy. EfficientNet architectures introduced a systematic compound scaling method to efficiently scale model width, depth, and resolution, yielding superior performance across various models. However, this scaling is predominantly static, pre-determined during design, and lacks adaptability to fluctuating or dynamic resource availability. This paper proposes the Adaptive EfficientNet, a novel framework that integrates dynamic compound scaling to achieve resource-optimal deep learning. We present a methodology for adjusting the EfficientNet's scaling parameters (width, depth, and resolution coefficients) on-the-fly or at deployment time based on real-time resource availability or predefined budget constraints, such as target latency, computational budget (FLOPS), or memory footprint. Our approach leverages a resource-aware optimization strategy to find the most efficient network configuration for a given set of constraints, thereby maximizing performance under limited resources. We demonstrate through extensive experimental analysis that Adaptive EfficientNet significantly outperforms statically scaled models by achieving comparable or superior accuracy with substantially reduced computational requirements or by providing improved accuracy within strict resource envelopes. This work paves the way for more flexible and efficient deployment of deep learning models in heterogeneous and resource-constrained environments, offering a crucial advancement towards ubiquitous and sustainable AI.

Type

article

Landing Page

https://doi.org/10.5281/zenodo.17822377

OA Status

green

OpenAlex ID

https://openalex.org/W7108645210

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W7108645210

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.5281/zenodo.17822377

Digital Object Identifier

Title

Adaptive EfficientNet: Dynamic Compound Scaling for Resource-Optimal Deep Learning

Work title

Type

article

OpenAlex work type

Publication year

2025

Year of publication

Publication date

2025-12-04

Full publication date if available

Authors

Revista, Zen, IA, 10

List of authors in order

Landing page

https://doi.org/10.5281/zenodo.17822377

Publisher landing page

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://doi.org/10.5281/zenodo.17822377

Direct OA link when available

Concepts

Software deployment, Computer science, Adaptability, Deep learning, Resource (disambiguation), Scaling, Distributed computing, Artificial intelligence, Set (abstract data type), Artificial neural network, Adaptation (eye), Scale (ratio), Resource allocation, Machine learning, Computational resource, Deep neural networks, Resource efficiency, Resource management (computing), Scheduling (production processes), Budget constraint, Edge device, Adaptive optimization

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Full payload