# Achieving Pareto Optimality using Efficient Parameter Reduction for DNNs in Resource-Constrained Edge Environment

arXiv: https://arxiv.org/abs/2403.10569 · HTML: https://mlsanity.com/paper/2403.10569/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 14 Mar 2024.

## Builds on (most cited first, 26 of 26)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions](https://mlsanity.com/paper/2006.02903/) (2020)
- [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://mlsanity.com/paper/2004.09602/) (2020)
- [Convergence of Edge Computing and Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/1907.08349/) (2019)
- [Loss Aware Post-training Quantization](https://mlsanity.com/paper/1911.07190/) (2019)
- [Communication-Efficient Edge AI: Algorithms and Systems](https://mlsanity.com/paper/2002.09668/) (2020)
- [Post-Training Piecewise Linear Quantization for Deep Neural Networks](https://mlsanity.com/paper/2002.00104/) (2020)
- [A Neural Network-Based On-device Learning Anomaly Detector for Edge Devices](https://mlsanity.com/paper/1907.10147/) (2019)
- [A PCB Dataset for Defects Detection and Classification](https://mlsanity.com/paper/1901.08204/) (2019)
- [HPTQ: Hardware-Friendly Post Training Quantization](https://mlsanity.com/paper/2109.09113/) (2021)
- [Training on the Edge: The why and the how](https://mlsanity.com/paper/1903.03051/) (2019)
- [Real-Time Human Detection as an Edge Service Enabled by a Lightweight CNN](https://mlsanity.com/paper/1805.00330/) (2018)
- [Fostering new Vertical and Horizontal IoT Applications with Intelligence Everywhere](https://mlsanity.com/paper/2310.00346/) (2023)
- [TransferD2: Automated Defect Detection Approach in Smart Manufacturing using Transfer Learning Techniques](https://mlsanity.com/paper/2302.13317/) (2023)

## Built on by (most cited first, 1 of 1)

- [SEval-NAS: A Search-Agnostic Evaluation for Neural Architecture Search](https://mlsanity.com/paper/2603.00099/) (2026)

## Abstract (arXiv)

This paper proposes an optimization of an existing Deep Neural Network (DNN) that improves its hardware utilization and facilitates on-device training for resource-constrained edge environments. We implement efficient parameter reduction strategies on Xception that shrink the model size without sacrificing accuracy, thus decreasing memory utilization during training. We evaluate our model in two experiments: Caltech-101 image classification and PCB defect detection and compare its performance against the original Xception and lightweight models, EfficientNetV2B1 and MobileNetV2. The results of the Caltech-101 image classification show that our model has a better test accuracy (76.21%) than Xception (75.89%), uses less memory on average (847.9MB) than Xception (874.6MB), and has faster training and inference times. The lightweight models overfit with EfficientNetV2B1 having a 30.52% test accuracy and MobileNetV2 having a 58.11% test accuracy. Both lightweight models have better memory usage than our model and Xception. On the PCB defect detection, our model has the best test accuracy (90.30%), compared to Xception (88.10%), EfficientNetV2B1 (55.25%), and MobileNetV2 (50.50%). MobileNetV2 has the least average memory usage (849.4MB), followed by our model (865.8MB), then EfficientNetV2B1 (874.8MB), and Xception has the highest (893.6MB). We further experiment with pre-trained weights and observe that memory usage decreases thereby showing the benefits of transfer learning. A Pareto analysis of the models' performance shows that our optimized model architecture satisfies accuracy and low memory utilization objectives.