Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Nicholas D. Lane

Nicholas D. Lane

Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions


Jun 09, 2021
Stefanos Laskaridis, Alexandros Kouris, Nicholas D. Lane

Figure 1 for Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
Figure 2 for Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
Figure 3 for Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
* Accepted at the 5th Annual International Workshop on Embedded and Mobile Deep Learning (EMDL), 2021 
  Access Paper or Ask Questions

Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions


Jun 07, 2021
Royson Lee, Stylianos I. Venieris, Nicholas D. Lane

Figure 1 for Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions
Figure 2 for Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions
Figure 3 for Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions
Figure 4 for Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions
* Accepted for publication at the ACM Computing Surveys (CSUR) journal, 2021. arXiv admin note: text overlap with arXiv:2010.05838 
  Access Paper or Ask Questions

Multi-Exit Semantic Segmentation Networks


Jun 07, 2021
Alexandros Kouris, Stylianos I. Venieris, Stefanos Laskaridis, Nicholas D. Lane

Figure 1 for Multi-Exit Semantic Segmentation Networks
Figure 2 for Multi-Exit Semantic Segmentation Networks
Figure 3 for Multi-Exit Semantic Segmentation Networks
Figure 4 for Multi-Exit Semantic Segmentation Networks

  Access Paper or Ask Questions

End-to-End Speech Recognition from Federated Acoustic Models


Apr 29, 2021
Yan Gao, Titouan Parcollet, Javier Fernandez-Marques, Pedro P. B. de Gusmao, Daniel J. Beutel, Nicholas D. Lane

Figure 1 for End-to-End Speech Recognition from Federated Acoustic Models
Figure 2 for End-to-End Speech Recognition from Federated Acoustic Models
Figure 3 for End-to-End Speech Recognition from Federated Acoustic Models

  Access Paper or Ask Questions

DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device


Apr 20, 2021
Mario Almeida, Stefanos Laskaridis, Stylianos I. Venieris, Ilias Leontiadis, Nicholas D. Lane

Figure 1 for DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device
Figure 2 for DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device
Figure 3 for DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device
Figure 4 for DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device
* Under review 
  Access Paper or Ask Questions

Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions


Apr 10, 2021
Shyam A. Tailor, Felix L. Opolka, Pietro Liò, Nicholas D. Lane

Figure 1 for Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions
Figure 2 for Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions
Figure 3 for Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions
Figure 4 for Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions
* Short versions to appear at the GNNSys Workshop at MLSys 2021 and the Hardware-Aware Efficient Training Workshop at ICLR 2021 
  Access Paper or Ask Questions

On-device Federated Learning with Flower


Apr 07, 2021
Akhil Mathur, Daniel J. Beutel, Pedro Porto Buarque de Gusmão, Javier Fernandez-Marques, Taner Topal, Xinchi Qiu, Titouan Parcollet, Yan Gao, Nicholas D. Lane

Figure 1 for On-device Federated Learning with Flower
Figure 2 for On-device Federated Learning with Flower
Figure 3 for On-device Federated Learning with Flower
Figure 4 for On-device Federated Learning with Flower
* On-device Intelligence Workshop at the Fourth Conference on Machine Learning and Systems (MLSys), April 9, 2021 
 * Accepted at the 2nd On-device Intelligence Workshop @ MLSys 2021. arXiv admin note: substantial text overlap with arXiv:2007.14390 
  Access Paper or Ask Questions

unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generation


Apr 03, 2021
Stylianos I. Venieris, Javier Fernandez-Marques, Nicholas D. Lane

Figure 1 for unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generation
Figure 2 for unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generation
Figure 3 for unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generation
Figure 4 for unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generation
* Accepted at the 29th IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM) 2021 
  Access Paper or Ask Questions

FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout


Mar 01, 2021
Samuel Horvath, Stefanos Laskaridis, Mario Almeida, Ilias Leontiadis, Stylianos I. Venieris, Nicholas D. Lane

Figure 1 for FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
Figure 2 for FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
Figure 3 for FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
Figure 4 for FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout

  Access Paper or Ask Questions

A first look into the carbon footprint of federated learning


Feb 15, 2021
Xinchi Qiu, Titouan Parcollet, Javier Fernandez-Marques, Pedro Porto Buarque de Gusmao, Daniel J. Beutel, Taner Topal, Akhil Mathur, Nicholas D. Lane

Figure 1 for A first look into the carbon footprint of federated learning
Figure 2 for A first look into the carbon footprint of federated learning
Figure 3 for A first look into the carbon footprint of federated learning
Figure 4 for A first look into the carbon footprint of federated learning
* arXiv admin note: substantial text overlap with arXiv:2010.06537 
  Access Paper or Ask Questions

It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation


Feb 02, 2021
Ilias Leontiadis, Stefanos Laskaridis, Stylianos I. Venieris, Nicholas D. Lane

Figure 1 for It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation
Figure 2 for It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation
Figure 3 for It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation
Figure 4 for It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation
* Accepted at the 22nd International Workshop on Mobile Computing Systems and Applications (HotMobile), 2021 
  Access Paper or Ask Questions

Zero-Cost Proxies for Lightweight NAS


Jan 20, 2021
Mohamed S. Abdelfattah, Abhinav Mehrotra, Łukasz Dudziak, Nicholas D. Lane

Figure 1 for Zero-Cost Proxies for Lightweight NAS
Figure 2 for Zero-Cost Proxies for Lightweight NAS
Figure 3 for Zero-Cost Proxies for Lightweight NAS
Figure 4 for Zero-Cost Proxies for Lightweight NAS
* accepted at ICLR 2021 
  Access Paper or Ask Questions

Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous Data


Nov 16, 2020
Chongyang Wang, Yuan Gao, Akhil Mathur, Amanda C. De C. Williams, Nicholas D. Lane, Nadia Bianchi-Berthouze

Figure 1 for Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous Data
Figure 2 for Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous Data
Figure 3 for Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous Data
Figure 4 for Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous Data

  Access Paper or Ask Questions

$μ$NAS: Constrained Neural Architecture Search for Microcontrollers


Nov 04, 2020
Edgar Liberis, Łukasz Dudziak, Nicholas D. Lane

Figure 1 for $μ$NAS: Constrained Neural Architecture Search for Microcontrollers
Figure 2 for $μ$NAS: Constrained Neural Architecture Search for Microcontrollers
Figure 3 for $μ$NAS: Constrained Neural Architecture Search for Microcontrollers
Figure 4 for $μ$NAS: Constrained Neural Architecture Search for Microcontrollers
* $\mu$NAS is available at https://github.com/eliberis/uNAS v2 change: corrected baseline, expanded text 
  Access Paper or Ask Questions

Neural Enhancement in Content Delivery Systems: The State-of-the-Art and Future Directions


Oct 22, 2020
Royson Lee, Stylianos I. Venieris, Nicholas D. Lane

Figure 1 for Neural Enhancement in Content Delivery Systems: The State-of-the-Art and Future Directions
Figure 2 for Neural Enhancement in Content Delivery Systems: The State-of-the-Art and Future Directions
Figure 3 for Neural Enhancement in Content Delivery Systems: The State-of-the-Art and Future Directions
Figure 4 for Neural Enhancement in Content Delivery Systems: The State-of-the-Art and Future Directions
* Accepted at the 1st Workshop on Distributed Machine Learning at CoNEXT 2020 (DistributedML 2020) 
  Access Paper or Ask Questions

Deep Learning in the Era of Edge Computing: Challenges and Opportunities


Oct 17, 2020
Mi Zhang, Faen Zhang, Nicholas D. Lane, Yuanchao Shu, Xiao Zeng, Biyi Fang, Shen Yan, Hui Xu

Figure 1 for Deep Learning in the Era of Edge Computing: Challenges and Opportunities
Figure 2 for Deep Learning in the Era of Edge Computing: Challenges and Opportunities
Figure 3 for Deep Learning in the Era of Edge Computing: Challenges and Opportunities
Figure 4 for Deep Learning in the Era of Edge Computing: Challenges and Opportunities

  Access Paper or Ask Questions

Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptation


Sep 06, 2020
Akhil Mathur, Fahim Kawsar, Nadia Berthouze, Nicholas D. Lane

Figure 1 for Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptation
Figure 2 for Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptation
Figure 3 for Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptation
Figure 4 for Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptation
* 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 7439-7443 
 * 5 pages, Published at IEEE ICASSP 2020 
  Access Paper or Ask Questions

SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud


Aug 24, 2020
Stefanos Laskaridis, Stylianos I. Venieris, Mario Almeida, Ilias Leontiadis, Nicholas D. Lane

Figure 1 for SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud
Figure 2 for SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud
Figure 3 for SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud
Figure 4 for SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud
* Accepted at the 26th Annual International Conference on Mobile Computing and Networking (MobiCom), 2020 
  Access Paper or Ask Questions

Degree-Quant: Quantization-Aware Training for Graph Neural Networks


Aug 11, 2020
Shyam A. Tailor, Javier Fernandez-Marques, Nicholas D. Lane

Figure 1 for Degree-Quant: Quantization-Aware Training for Graph Neural Networks
Figure 2 for Degree-Quant: Quantization-Aware Training for Graph Neural Networks
Figure 3 for Degree-Quant: Quantization-Aware Training for Graph Neural Networks
Figure 4 for Degree-Quant: Quantization-Aware Training for Graph Neural Networks

  Access Paper or Ask Questions

Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems


Aug 11, 2020
Ravichander Vipperla, Sangjun Park, Kihyun Choo, Samin Ishtiaq, Kyoungbo Min, Sourav Bhattacharya, Abhinav Mehrotra, Alberto Gil C. P. Ramos, Nicholas D. Lane

Figure 1 for Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems
Figure 2 for Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems
Figure 3 for Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems
Figure 4 for Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems
* Interspeech 2020 
  Access Paper or Ask Questions

BRP-NAS: Prediction-based NAS using GCNs


Aug 10, 2020
Łukasz Dudziak, Thomas Chau, Mohamed S. Abdelfattah, Royson Lee, Hyeji Kim, Nicholas D. Lane

Figure 1 for BRP-NAS: Prediction-based NAS using GCNs
Figure 2 for BRP-NAS: Prediction-based NAS using GCNs
Figure 3 for BRP-NAS: Prediction-based NAS using GCNs
Figure 4 for BRP-NAS: Prediction-based NAS using GCNs

  Access Paper or Ask Questions