# Neural Network Compression Framework for fast model inference

arXiv: https://arxiv.org/abs/2002.08679 · HTML: https://mlsanity.com/paper/2002.08679/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2020.

## Built on by (most cited first, 18 of 18)

- [Anomalib: A Deep Learning Library for Anomaly Detection](https://mlsanity.com/paper/2202.08341/) (2022)
- [MQBench: Towards Reproducible and Deployable Model Quantization Benchmark](https://mlsanity.com/paper/2111.03759/) (2021)
- [Effective Interplay between Sparsity and Quantization: From Theory to Practice](https://mlsanity.com/paper/2405.20935/) (2024)
- [SparseDNN: Fast Sparse Deep Learning Inference on CPUs](https://mlsanity.com/paper/2101.07948/) (2021)
- [Enabling NAS with Automated Super-Network Generation](https://mlsanity.com/paper/2112.10878/) (2021)
- [Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization](https://mlsanity.com/paper/2106.07611/) (2021)
- [Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices](https://mlsanity.com/paper/2103.03483/) (2021)
- [Learn from Foundation Model: Fruit Detection Model without Manual Annotation](https://mlsanity.com/paper/2411.16196/) (2024)
- [Side-Channel Analysis of OpenVINO-based Neural Network Models](https://mlsanity.com/paper/2407.16467/) (2024)
- [CheckINN: Wide Range Neural Network Verification in Imandra (Extended)](https://mlsanity.com/paper/2207.10562/) (2022)
- [QFT: Post-training quantization via fast joint finetuning of all degrees of freedom](https://mlsanity.com/paper/2212.02634/) (2022)
- [Benchmarking Adversarial Robustness of Compressed Deep Learning Models](https://mlsanity.com/paper/2308.08160/) (2023)
- [EfficientBioAI: Making Bioimaging AI Models Efficient in Energy, Latency and Representation](https://mlsanity.com/paper/2306.06152/) (2023)
- [PowerYOLO: Mixed Precision Model for Hardware Efficient Object Detection with Event Data](https://mlsanity.com/paper/2407.08272/) (2024)
- [Model Compression](https://mlsanity.com/paper/2105.10059/) (2021)
- [Predicting the success of Gradient Descent for a particular Dataset-Architecture-Initialization (DAI)](https://mlsanity.com/paper/2111.13075/) (2021)
- [Quantization Range Estimation for Convolutional Neural Networks](https://mlsanity.com/paper/2510.04044/) (2025)
- [GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine](https://mlsanity.com/paper/2607.00544/) (2026)

## Abstract (arXiv)

In this work we present a new framework for neural networks compression with fine-tuning, which we called Neural Network Compression Framework (NNCF). It leverages recent advances of various network compression methods and implements some of them, such as sparsity, quantization, and binarization. These methods allow getting more hardware-friendly models which can be efficiently run on general-purpose hardware computation units (CPU, GPU) or special Deep Learning accelerators. We show that the developed methods can be successfully applied to a wide range of models to accelerate the inference time while keeping the original accuracy. The framework can be used within the training samples, which are supplied with it, or as a standalone package that can be seamlessly integrated into the existing training code with minimal adaptations. Currently, a PyTorch version of NNCF is available as a part of OpenVINO Training Extensions at https://github.com/openvinotoolkit/nncf.