mlsanityData to 7 Oct 2026

QONNX: Representing Arbitrary-Precision Quantized Neural Networks

arXiv 2206.07527 ↗First posted 15 Jun 2022cs.LG cs.AR cs.PLcited by 9

Not on the map. Why?

Abstract (arXiv)

We present extensions to the Open Neural Network Exchange (ONNX) intermediate representation format to represent arbitrary-precision quantized neural networks. We first introduce support for low precision quantization in existing ONNX-based quantization formats by leveraging integer clipping, resulting in two new backward-compatible variants: the quantized operator format with clipping and quantize-clip-dequantize (QCDQ) format. We then introduce a novel higher-level ONNX format called quantized ONNX (QONNX) that introduces three new operators -- Quant, BipolarQuant, and Trunc -- in order to represent uniform quantization. By keeping the QONNX IR high-level and flexible, we enable targeting a wider variety of platforms. We also present utilities for working with QONNX, as well as examples of its usage in the FINN and hls4ml toolchains. Finally, we introduce the QONNX model zoo to share low-precision quantized neural networks.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 15 of its 29 references that are in the map. First posted on arXiv 15 Jun 2022.

Builds on

15 of 29 references.

References · 15

  1. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  2. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  3. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  4. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  5. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  6. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 387
  7. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 250
  8. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  9. 2016FINN: A Framework for Fast, Scalable Binarized Neural Network Inferencecited by 141
  10. 2018Fast inference of deep neural networks in FPGAs for particle physicscited by 132
  11. 2020Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectorscited by 78
  12. 2018FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networkscited by 54
3 more
  1. 2020Efficient Execution of Quantized Deep Learning Models: A Compiler Approachcited by 12
  2. 2020Efficient Residue Number System Based Winograd Convolutioncited by 5
  3. 2021Pre-Quantized Deep Learning Models Codified in ONNX to Enable Hardware/Software Co-Designcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 3; 2026: 3.

9 papers.

  1. 2022Open-source FPGA-ML codesign for the MLPerf Tiny Benchmarkcited by 9
  2. 2025hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardwarecited by 8
  3. 2023End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICscited by 1
  4. 2024NaviSplit: Dynamic Multi-Branch Split DNNs for Efficient Distributed Autonomous Navigationcited by 1
  5. 2025FINN-GL: Generalized Mixed-Precision Extensions for FPGA-Accelerated LSTMscited by 0
  6. 2025Hardware-Aware Feature Extraction Quantisation for Real-Time Visual Odometry on FPGA Platformscited by 0
  7. 2026ALADIN: Accuracy-Latency-Aware Design-space Inference Analysis for Embedded AI Acceleratorscited by 0
  8. 2026CADENCE: Context-Adaptive Depth Estimation for Navigation and Computational Efficiencycited by 0
  9. 2026QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networkscited by 0