# Toward Efficient Convolutional Neural Networks With Structured Ternary Patterns

arXiv: https://arxiv.org/abs/2407.14831 · HTML: https://mlsanity.com/paper/2407.14831/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 47 references that are in the map.
- First posted on arXiv 20 Jul 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [Trained Ternary Quantization](https://mlsanity.com/paper/1612.01064/) (2016)
- [Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better](https://mlsanity.com/paper/2106.08962/) (2021)
- [AdaBits: Neural Network Quantization with Adaptive Bit-Widths](https://mlsanity.com/paper/1912.09666/) (2019)
- [Ternary Compression for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2003.03564/) (2020)
- [Pelee: A Real-Time Object Detection System on Mobile Devices](https://mlsanity.com/paper/1804.06882/) (2018)
- [Local Binary Convolutional Neural Networks](https://mlsanity.com/paper/1608.06049/) (2016)
- [Pareto-Optimal Quantized ResNet Is Mostly 4-bit](https://mlsanity.com/paper/2105.03536/) (2021)
- [EDropout: Energy-Based Dropout and Pruning of Deep Neural Networks](https://mlsanity.com/paper/2006.04270/) (2020)
- [Bit Efficient Quantization for Deep Neural Networks](https://mlsanity.com/paper/1910.04877/) (2019)
- [Quantization-Guided Training for Compact TinyML Models](https://mlsanity.com/paper/2103.06231/) (2021)
- [Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report](https://mlsanity.com/paper/2105.08819/) (2021)
- [Local Binary Pattern Networks](https://mlsanity.com/paper/1803.07125/) (2018)

## Abstract (arXiv)

High-efficiency deep learning (DL) models are necessary not only to facilitate their use in devices with limited resources but also to improve resources required for training. Convolutional neural networks (ConvNets) typically exert severe demands on local device resources and this conventionally limits their adoption within mobile and embedded platforms. This brief presents work toward utilizing static convolutional filters generated from the space of local binary patterns (LBPs) and Haar features to design efficient ConvNet architectures. These are referred to as Structured Ternary Patterns (STePs) and can be generated during network initialization in a systematic way instead of having learnable weight parameters thus reducing the total weight updates. The ternary values require significantly less storage and with the appropriate low-level implementation, can also lead to inference improvements. The proposed approach is validated using four image classification datasets, demonstrating that common network backbones can be made more efficient and provide competitive results. It is also demonstrated that it is possible to generate completely custom STeP-based networks that provide good trade-offs for on-device applications such as unmanned aerial vehicle (UAV)-based aerial vehicle detection. The experimental results show that the proposed method maintains high detection accuracy while reducing the trainable parameters by 40-80%. This work motivates further research toward good priors for non-learnable weights that can make DL architectures more efficient without having to alter the network during or after training.