Bit-serial Weight Pools: Compression and Arbitrary Precision Execution of Neural Networks on Resource Constrained Processors
Not on the map. Why?
Abstract (arXiv)
Applications of neural networks on edge systems have proliferated in recent years but the ever-increasing model size makes neural networks not able to deploy on resource-constrained microcontrollers efficiently. We propose bit-serial weight pools, an end-to-end framework that includes network compression and acceleration of arbitrary sub-byte precision. The framework can achieve up to 8x compression compared to 8-bit networks by sharing a pool of weights across the entire network. We further propose a bit-serial lookup based software implementation that allows runtime-bitwidth tradeoff and is able to achieve more than 2.8x speedup and 7.5x storage compression compared to 8-bit weight pool networks, with less than 1% accuracy drop.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 11 of its 22 references that are in the map. First posted on arXiv 25 Jan 2022.
Builds on
11 of 22 references.
References · 11
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
- 2021MLPerf Tiny Benchmarkcited by 118
- 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 116
- 2017Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networkscited by 95
- 2018Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutionscited by 33
- 2018A Quantization-Friendly Separable Convolution for MobileNetscited by 22
- 2021Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamicscited by 12
- 2018Automating Generation of Low Precision Deep Learning Operatorscited by 6
- 2021SWIS -- Shared Weight bIt Sparsity for Efficient Neural Network Accelerationcited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.