mlsanityData to 14 Oct 2026

ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA

arXiv 2111.00155 ↗First posted 30 Oct 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This work targets the commonly used FPGA (field-programmable gate array) devices as the hardware platform for DNN edge computing. We focus on DNN quantization as the main model compression technique. The novelty of this work is: We use a quantization method that supports multiple precisions along the intra-layer dimension, while the existing quantization methods apply multi-precision quantization along the inter-layer dimension. The intra-layer multi-precision method can uniform the hardware configurations for different layers to reduce computation overhead and at the same time preserve the model accuracy as the inter-layer approach. Our proposed ILMPQ DNN quantization framework achieves 70.73 Top1 accuracy in ResNet-18 on the ImageNet dataset. We also validate the proposed MSP framework on two FPGA devices i.e., Xilinx XC7Z020 and XC7Z045. We achieve 3.65x speedup in end-to-end inference time on the ImageNet, compared with the fixed-point quantization method.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 6 references that are in the map. First posted on arXiv 30 Oct 2021.

Builds on

6 of 6 references.

References · 6

  1. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  2. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
  3. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  4. 2016Ternary Weight Networkscited by 204
  5. 2016Convolutional Neural Networks using Logarithmic Data Representationcited by 99
  6. 2020Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Frameworkcited by 27

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization
  2. 2021BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratch
  3. 2022FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation
  4. 2023On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks
  5. 2025Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference
  6. 2022Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks
  7. 2026SigmaQuant: Hardware-Aware Heterogeneous Quantization Method for Edge DNN Inference
  8. 2023Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge