no code implementations • ICML 2020 • Aditya Rajagopal, Diederik Vink, Stylianos Venieris, Christos-Savvas Bouganis
Large-scale convolutional neural networks (CNNs) suffer from very long training times, spanning from hours to weeks, limiting the productivity and experimentation of deep learning practitioners.
no code implementations • 27 Mar 2024 • Petros Toupas, Zhewen Yu, Christos-Savvas Bouganis, Dimitrios Tzovaras
Convolutional Neural Networks (CNNs) have demonstrated their effectiveness in numerous vision tasks.
no code implementations • 19 Mar 2024 • Guoxuan Xia, Olivier Laurent, Gianni Franchi, Christos-Savvas Bouganis
We first demonstrate empirically across a range of tasks and architectures that LS leads to a consistent degradation in SC.
no code implementations • 4 Sep 2023 • Alexander Montgomerie-Corcoran, Petros Toupas, Zhewen Yu, Christos-Savvas Bouganis
The YOLO family of models is considered the most efficient for object detection, having only a single model pass.
1 code implementation • 8 Jun 2023 • Zhewen Yu, Christos-Savvas Bouganis
The deployment of neural networks to such dataflow architecture accelerators is usually hindered by the available on-chip memory as it is desirable to preload the weights of neural networks on-chip to maximise the system performance.
no code implementations • 31 May 2023 • Petros Toupas, Christos-Savvas Bouganis, Dimitrios Tzovaras
A variety of 3D CNN models were evaluated using the proposed toolflow on multiple FPGA devices, demonstrating its potential to deliver competitive performance compared to earlier hand-tuned and model-specific designs.
no code implementations • 29 May 2023 • Petros Toupas, Christos-Savvas Bouganis, Dimitrios Tzovaras
3D Convolutional Neural Networks are gaining increasing attention from researchers and practitioners and have found applications in many domains, such as surveillance systems, autonomous vehicles, human monitoring systems, and video retrieval.
no code implementations • 17 Apr 2023 • Benjamin Biggs, Christos-Savvas Bouganis, George A. Constantinides
Additionally, the toolflow can achieve a throughput matching the same baseline with as low as $46\%$ of the resources the baseline requires.
2 code implementations • 30 Mar 2023 • Petros Toupas, Alexander Montgomerie-Corcoran, Christos-Savvas Bouganis, Dimitrios Tzovaras
For Human Action Recognition tasks (HAR), 3D Convolutional Neural Networks have proven to be highly effective, achieving state-of-the-art results.
1 code implementation • ICCV 2023 • Guoxuan Xia, Christos-Savvas Bouganis
Experiments on ImageNet-scale data across a number of network architectures and uncertainty tasks show that the proposed window-based early-exit approach is able to achieve a superior uncertainty-computation trade-off compared to scaling single models.
1 code implementation • 22 Aug 2022 • Zhewen Yu, Christos-Savvas Bouganis
The task of compressing pre-trained Deep Neural Networks has attracted wide interest of the research community due to its great benefits in freeing practitioners from data access requirements.
1 code implementation • 15 Jul 2022 • Guoxuan Xia, Christos-Savvas Bouganis
As such we show that practically, even better OOD detection performance can be achieved for Deep Ensembles by averaging task-specific detection scores such as Energy over the ensemble.
1 code implementation • 15 Jul 2022 • Guoxuan Xia, Christos-Savvas Bouganis
However, the performance of detection methods is generally evaluated on the task in isolation, rather than also considering potential downstream tasks in tandem.
no code implementations • 19 May 2022 • Stylianos I. Venieris, Christos-Savvas Bouganis, Nicholas D. Lane
As the use of AI-powered applications widens across multiple domains, so do increase the computational demands.
no code implementations • 1 Mar 2022 • Aditya Rajagopal, Christos-Savvas Bouganis
Consequently, it is likely that the observed data distribution upon deployment is a subset of the training data distribution.
1 code implementation • 12 Aug 2021 • Aditya Rajagopal, Christos-Savvas Bouganis
The increased memory and processing capabilities of today's edge devices create opportunities for greater edge intelligence.
1 code implementation • 18 Jun 2020 • Diederik Adriaan Vink, Aditya Rajagopal, Stylianos I. Venieris, Christos-Savvas Bouganis
CNN training on FPGAs is a nascent field of research.
no code implementations • 16 Jun 2020 • Aditya Rajagopal, Diederik Adriaan Vink, Stylianos I. Venieris, Christos-Savvas Bouganis
Large-scale convolutional neural networks (CNNs) suffer from very long training times, spanning from hours to weeks, limiting the productivity and experimentation of deep learning practitioners.
1 code implementation • 15 Jun 2020 • Aditya Rajagopal, Christos-Savvas Bouganis
In today's world, a vast amount of data is being generated by edge devices that can be used as valuable training data to improve the performance of machine learning algorithms in terms of the achieved accuracy or to reduce the compute requirements of the model.
no code implementations • 2 May 2019 • Alexandros Kouris, Stylianos I. Venieris, Michail Rizakis, Christos-Savvas Bouganis
The need to recognise long-term dependencies in sequential data such as video streams has made Long Short-Term Memory (LSTM) networks a prominent Artificial Intelligence model for many emerging applications.
2 code implementations • 18 Jul 2018 • Christos Kyrkou, George Plastiras, Stylianos Venieris, Theocharis Theocharides, Christos-Savvas Bouganis
Through the analysis we propose a CNN architecture that is capable of detecting vehicles from aerial UAV images and can operate between 5-18 frames-per-second for a variety of platforms with an overall accuracy of ~95%.
Object Detection In Aerial Images One-Shot Object Detection +1
no code implementations • 13 Jul 2018 • 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.
no code implementations • 22 Jun 2018 • Stylianos I. Venieris, Alexandros Kouris, Christos-Savvas Bouganis
Recently, Deep Neural Networks (DNNs) have emerged as the dominant model across various AI applications.
no code implementations • 25 May 2018 • Stylianos I. Venieris, Christos-Savvas Bouganis
The predictive power of Convolutional Neural Networks (CNNs) has been an integral factor for emerging latency-sensitive applications, such as autonomous drones and vehicles.
no code implementations • 22 May 2018 • 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.
no code implementations • 15 Mar 2018 • Stylianos I. Venieris, Alexandros Kouris, Christos-Savvas Bouganis
In the past decade, Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance in various Artificial Intelligence tasks.
no code implementations • 7 Jan 2018 • Michalis Rizakis, Stylianos I. Venieris, Alexandros Kouris, Christos-Savvas Bouganis
Recurrent Neural Networks and in particular Long Short-Term Memory (LSTM) networks have demonstrated state-of-the-art accuracy in several emerging Artificial Intelligence tasks.
no code implementations • 23 Nov 2017 • Stylianos I. Venieris, Christos-Savvas Bouganis
By selectively optimising for throughput, latency or multiobjective criteria, the presented tool is able to efficiently explore the design space and generate hardware designs from high-level ConvNet specifications, explicitly optimised for the performance metric of interest.
no code implementations • CVPR 2015 • Yonggang Jin, Christos-Savvas Bouganis
This paper proposes a robust multi-image based blind face hallucination framework to super-resolve LR faces.