mlsanityData to 7 Oct 2026

FINN: A Framework for Fast, Scalable Binarized Neural Network Inference

arXiv 1612.07119 ↗First posted 1 Dec 2016cs.CV cs.AR cs.LGcited by 141

Not on the map. Why?

Abstract (arXiv)

Research has shown that convolutional neural networks contain significant redundancy, and high classification accuracy can be obtained even when weights and activations are reduced from floating point to binary values. In this paper, we present FINN, a framework for building fast and flexible FPGA accelerators using a flexible heterogeneous streaming architecture. By utilizing a novel set of optimizations that enable efficient mapping of binarized neural networks to hardware, we implement fully connected, convolutional and pooling layers, with per-layer compute resources being tailored to user-provided throughput requirements. On a ZC706 embedded FPGA platform drawing less than 25 W total system power, we demonstrate up to 12.3 million image classifications per second with 0.31 μs latency on the MNIST dataset with 95.8% accuracy, and 21906 image classifications per second with 283 μs latency on the CIFAR-10 and SVHN datasets with respectively 80.1% and 94.9% accuracy. To the best of our knowledge, ours are the fastest classification rates reported to date on these benchmarks.

Key facts. Cited by 141 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 27; 2022: 16; 2023: 30; 2024: 21; 2025: 21; 2026: 26.

141 papers.

Sort:

By area:

  1. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  2. 2022Deep Differentiable Logic Gate Networkscited by 67
  3. 2021hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devicescited by 61
  4. 2021Fast convolutional neural networks on FPGAs with hls4mlcited by 42
  5. 2024Convolutional Differentiable Logic Gate Networkscited by 37
  6. 2021Applications and Techniques for Fast Machine Learning in Sciencecited by 32
  7. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  8. 2021Ps and Qs: Quantization-aware pruning for efficient low latency neural network inferencecited by 31
  9. 2023PolyLUT: Learning Piecewise Polynomials for Ultra-Low Latency FPGA LUT-based Inferencecited by 30
  10. 2023Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inferencecited by 29
  11. 2023A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networkscited by 23
  12. 2023A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platformscited by 21
38 more
  1. 2024NeuraLUT: Hiding Neural Network Density in Boolean Synthesizable Functionscited by 21
  2. 2021HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Searchcited by 20
  3. 2021Charged particle tracking via edge-classifying interaction networkscited by 19
  4. 2021Information Theoretic Representation Distillationcited by 19
  5. 2021"BNN - BN = ?": Training Binary Neural Networks without Batch Normalizationcited by 17
  6. 2021ROBIN: A Robust Optical Binary Neural Network Acceleratorcited by 15
  7. 2025TreeLUT: An Efficient Alternative to Deep Neural Networks for Inference Acceleration Using Gradient Boosted Decision Treescited by 15
  8. 2025NeuraLUT-Assemble: Hardware-aware Assembling of Sub-Neural Networks for Efficient LUT Inferencecited by 14
  9. 2025KANEL'E: Kolmogorov-Arnold Networks for Efficient LUT-based Evaluationcited by 13
  10. 2021SECDA: Efficient Hardware/Software Co-Design of FPGA-based DNN Accelerators for Edge Inferencecited by 12
  11. 2022Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challengescited by 12
  12. 2024PolyLUT-Add: FPGA-based LUT Inference with Wide Inputscited by 12
  13. 2021Enabling Binary Neural Network Training on the Edgecited by 11
  14. 2022CFU Playground: Full-Stack Open-Source Framework for Tiny Machine Learning (tinyML) Acceleration on FPGAscited by 11
  15. 2022A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devicescited by 11
  16. 2023DeepAxe: A Framework for Exploration of Approximation and Reliability Trade-offs in DNN Acceleratorscited by 11
  17. 2023A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidancecited by 11
  18. 2024Learning Interpretable Differentiable Logic Networkscited by 10
  19. 2022QONNX: Representing Arbitrary-Precision Quantized Neural Networkscited by 9
  20. 2022Open-source FPGA-ML codesign for the MLPerf Tiny Benchmarkcited by 9
  21. 2024Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Acceleratorscited by 9
  22. 2024HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAscited by 9
  23. 2025PolyLUT: Ultra-low Latency Polynomial Inference with Hardware-Aware Structured Pruningcited by 8
  24. 2025hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardwarecited by 8
  25. 2021BinaryCoP: Binary Neural Network-based COVID-19 Face-Mask Wear and Positioning Predictor on Edge Devicescited by 7
  26. 2023FPGA Resource-aware Structured Pruning for Real-Time Neural Networkscited by 7
  27. 2023HARFLOW3D: A Latency-Oriented 3D-CNN Accelerator Toolflow for HAR on FPGA Devicescited by 5
  28. 2023An Encoding Framework for Binarized Images using HyperDimensional Computingcited by 5
  29. 2024PIM-Opt: Demystifying Distributed Optimization Algorithms on a Real-World Processing-In-Memory Systemcited by 5
  30. 2021unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generationcited by 4
  31. 2023Reaching the Edge of the Edge: Image Analysis in Spacecited by 4
  32. 2023Resilience of Deep Learning applications: a systematic literature review of analysis and hardening techniquescited by 4
  33. 2025MetaML-Pro: Cross-Stage Design Flow Automation for Efficient Deep Learning Accelerationcited by 4
  34. 2025A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMscited by 4
  35. 20213U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Accelerationcited by 3
  36. 2021Logic Shrinkage: Learned FPGA Netlist Sparsity for Efficient Neural Network Inferencecited by 3
  37. 2023Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidancecited by 3
  38. 2023Moby: Empowering 2D Models for Efficient Point Cloud Analytics on the Edgecited by 3

50 most cited of 141 All 141 (JSON)