# CascadeCNN: Pushing the Performance Limits of Quantisation in Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1807.05053 · HTML: https://mlsanity.com/paper/1807.05053/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2018.

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

- [DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device](https://mlsanity.com/paper/2104.09949/) (2021)
- [ATHEENA: A Toolflow for Hardware Early-Exit Network Automation](https://mlsanity.com/paper/2304.08400/) (2023)
- [FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation](https://mlsanity.com/paper/2203.12091/) (2022)
- [Fixed-point quantization aware training for on-device keyword-spotting](https://mlsanity.com/paper/2303.02284/) (2023)
- [Cascaded Classifier for Pareto-Optimal Accuracy-Cost Trade-Off Using off-the-Shelf ANNs](https://mlsanity.com/paper/2110.14256/) (2021)

## Abstract (arXiv)

This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, aiming to perform high-throughput inference. A two-stage architecture tailored for any given CNN-FPGA pair is generated, consisting of a low- and high-precision unit in a cascade. A confidence evaluation unit is employed to identify misclassified cases from the excessively low-precision unit and forward them to the high-precision unit for re-processing. Experiments demonstrate that the proposed toolflow can achieve a performance boost up to 55% for VGG-16 and 48% for AlexNet over the baseline design for the same resource budget and accuracy, without the need of retraining the model or accessing the training data.