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

2018-07-13 · Alexandros Kouris, Stylianos I. Venieris, Christos-Savvas Bouganis

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.

📄 PDF Abstract BibTeX arXiv:1807.05053

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Local Response Normalization Local Response Normalization is a normalization layer that implements the idea of lateral inhibition. Lateral inhibition is a concept in neurobiology that refers to the…

Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

CascadeCNN: Pushing the performance limits of quantisation

2018-05-22 · Alexandros Kouris, Stylianos I. Venieris, Christos-Savvas Bouganis

This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, to perform high-throughput inference by exploiting the computation time-accuracy trade-off. Without the nee…

On the Accuracy of Point Localisation in a Circular Camera-Array

2016-02-24 · Alireza Ghasemi, Adam Scholefield, Martin Vetterli

Although many advances have been made in light-field and camera-array image processing, there is still a lack of thorough analysis of the localisation accuracy of different multi-camera systems. By considering the proble…

Optimisation of a Siamese Neural Network for Real-Time Energy Efficient Object Tracking

2020-07-01 · Dominika Przewlocka, Mateusz Wasala, Hubert Szolc, Krzysztof Blachut 외

In this paper the research on optimisation of visual object tracking using a Siamese neural network for embedded vision systems is presented. It was assumed that the solution shall operate in real-time, preferably for a …

Object Tracking Visual Object Tracking

Signal-Based Malware Classification Using 1D CNNs

2025-09-08 · Jack Wilkie, Hanan Hindy, Ivan Andonovic, Christos Tachtatzis 외 arxiv

Malware classification is a contemporary and ongoing challenge in cyber-security: modern obfuscation techniques are able to evade traditional static analysis, while dynamic analysis is too resource intensive to be deploy…

Malware Classification

A Study of Quantisation-aware Training on Time Series Transformer Models for Resource-constrained FPGAs

2023-10-04 · Tianheng Ling, Chao Qian, Lukas Einhaus, Gregor Schiele

This study explores the quantisation-aware training (QAT) on time series Transformer models. We propose a novel adaptive quantisation scheme that dynamically selects between symmetric and asymmetric schemes during the QA…

Time Series