paper-with-me

Papers

Complexity-Driven CNN Compression for Resource-constrained Edge AI

2022-08-26 · Muhammad Zawish, Steven Davy, Lizy Abraham

Recent advances in Artificial Intelligence (AI) on the Internet of Things (IoT)-enabled network edge has realized edge intelligence in several applications such as smart agriculture, smart hospitals, and smart factories by enabling low-latency and computational efficiency. However, deploying state-of-the-art Convolutional Neural Networks (CNNs) such as VGG-16 and ResNets on resource-constrained edge devices is practically infeasible due to their large number of parameters and floating-point operations (FLOPs). Thus, the concept of network pruning as a type of model compression is gaining attention for accelerating CNNs on low-power devices. State-of-the-art pruning approaches, either structured or unstructured do not consider the different underlying nature of complexities being exhibited by convolutional layers and follow a training-pruning-retraining pipeline, which results in additional computational overhead. In this work, we propose a novel and computationally efficient pruning pipeline by exploiting the inherent layer-level complexities of CNNs. Unlike typical methods, our proposed complexity-driven algorithm selects a particular layer for filter-pruning based on its contribution to overall network complexity. We follow a procedure that directly trains the pruned model and avoids the computationally complex ranking and fine-tuning steps. Moreover, we define three modes of pruning, namely parameter-aware (PA), FLOPs-aware (FA), and memory-aware (MA), to introduce versatile compression of CNNs. Our results show the competitive performance of our approach in terms of accuracy and acceleration. Lastly, we present a trade-off between different resources and accuracy which can be helpful for developers in making the right decisions in resource-constrained IoT environments.

📄 PDF Abstract BibTeX arXiv:2208.12816

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyModel CompressionNetwork Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks

2025-02-04 · Shihao Zhang, Rayan Saab

Deep neural networks have achieved state-of-the-art performance across numerous applications, but their high memory and computational demands present significant challenges, particularly in resource-constrained environme…

Low-rank compressionModel Compression

Model Compression for Resource-Constrained Mobile Robots

2022-07-20 · Timotheos Souroulla, Alberto Hata, Ahmad Terra, Özer Özkahraman 외

The number of mobile robots with constrained computing resources that need to execute complex machine learning models has been increasing during the past decade. Commonly, these robots rely on edge infrastructure accessi…

Knowledge DistillationmodelModel Compression

Resource Constrained Model Compression via Minimax Optimization for Spiking Neural Networks

2023-08-09 · Jue Chen, Huan Yuan, Jianchao Tan, Bin Chen 외

Brain-inspired Spiking Neural Networks (SNNs) have the characteristics of event-driven and high energy-efficient, which are different from traditional Artificial Neural Networks (ANNs) when deployed on edge devices such …

Model CompressionSparse Learning

Extreme Model Compression for Edge Vision-Language Models: Sparse Temporal Token Fusion and Adaptive Neural Compression

2025-11-23 · Md Tasnin Tanvir, Soumitra Das, Sk Md Abidar Rahaman, Ali Shiri Sichani arxiv

The demand for edge AI in vision-language tasks requires models that achieve real-time performance on resource-constrained devices with limited power and memory. This paper proposes two adaptive compression techniques --…

Event-based visionModel CompressionChange Detection

AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategy

2022-01-24 · Chunnan Wang, Hongzhi Wang, Xiangyu Shi

Model compression methods can reduce model complexity on the premise of maintaining acceptable performance, and thus promote the application of deep neural networks under resource constrained environments. Despite their …

Model Compression