# Fixed-point Factorized Networks

arXiv: https://arxiv.org/abs/1611.01972 · HTML: https://mlsanity.com/paper/1611.01972/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2016.

## Built on by (most cited first, 5 of 5)

- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization](https://mlsanity.com/paper/2403.07134/) (2024)
- [Ternary Quantization: A Survey](https://mlsanity.com/paper/2303.01505/) (2023)
- [Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration](https://mlsanity.com/paper/2106.09886/) (2021)
- [UWC: Unit-wise Calibration Towards Rapid Network Compression](https://mlsanity.com/paper/2201.06376/) (2022)

## Abstract (arXiv)

In recent years, Deep Neural Networks (DNN) based methods have achieved remarkable performance in a wide range of tasks and have been among the most powerful and widely used techniques in computer vision. However, DNN-based methods are both computational-intensive and resource-consuming, which hinders the application of these methods on embedded systems like smart phones. To alleviate this problem, we introduce a novel Fixed-point Factorized Networks (FFN) for pretrained models to reduce the computational complexity as well as the storage requirement of networks. The resulting networks have only weights of -1, 0 and 1, which significantly eliminates the most resource-consuming multiply-accumulate operations (MACs). Extensive experiments on large-scale ImageNet classification task show the proposed FFN only requires one-thousandth of multiply operations with comparable accuracy.