Yiannis Andreopoulos
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yiannis Andreopoulos has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Alhabib Abbas
Department of Electronic & Electrical Engineering University College London London U.K
6 shared publications - Abdullahi Mohammad
University College London
5 shared publications - Christos Masouros
University College London
5 shared publications - Francesco Renna
Department of Computer Science Department of Computer Science Department of Computer Science University of Porto & INESC-TEC University of Porto & INESC-TEC University of Porto & INESC-TEC
3 shared publications - Vasileios Giotsas
Cloudflare, London, United Kingdom
3 shared publications - Aaron Chadha
Electronic and Electrical Engineering Department, University College London, Roberts Building, Torrington Place, London, WC1E. 7JE, UK
2 shared publications
Latest Publications
- Open Access
- 16 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 4, 1334-1349
A Memory-Efficient Learning Framework for Symbol Level Precoding With Quantized NN Weights
This paper proposes a memory-efficient deep neural network (DNN) framework-based symbol level precoding (SLP). We focus on a DNN with realistic finite precision weights and adopt an unsupervised deep learning (DL) based SLP model (SLP-DNet). We apply a stochastic quantization (SQ) technique to obtain its corresponding quantized version called SLP-SQDNet. The proposed scheme offers a scalable performance vs memory trade-off, by quantizing a scalable percentage of the DNN weights, and we explore binary and ternary quantizations. Our results show that while SLP-DNet provides near-optimal performance, its quantized versions through SQ yield ~3.46× and ~2.64× model compression for binary-based and ternary-based SLP-SQDNets, respectively. We also find that our proposals offer ~20× and ~10× computational complexity reductions compared to SLP optimization-based and SLP-DNet, respectively.
- 16 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 4, 1334-1349
Open AccessA Memory-Efficient Learning Framework for Symbol Level Precoding With Quantized NN Weights
This paper proposes a memory-efficient deep neural network (DNN) framework-based symbol level precoding (SLP). We focus on a DNN with realistic finite precision weights and adopt an unsupervised deep learning (DL) based SLP model (SLP-DNet). We apply a stochastic quantization (SQ) technique to obtain its corresponding quantized version called SLP-SQDNet. The proposed scheme offers a scalable performance vs memory trade-off, by quantizing a scalable percentage of the DNN weights, and we explore binary and ternary quantizations. Our results show that while SLP-DNet provides near-optimal performance, its quantized versions through SQ yield ~3.46× and ~2.64× model compression for binary-based and ternary-based SLP-SQDNets, respectively. We also find that our proposals offer ~20× and ~10× computational complexity reductions compared to SLP optimization-based and SLP-DNet, respectively.
- Open Access
- 28 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 4, 1075-1090
An Unsupervised Deep Unfolding Framework for Robust Symbol-Level Precoding
Symbol Level Precoding (SLP) has attracted significant research interest due to its ability to exploit interference for energy-efficient transmission. This paper proposes an unsupervised deep-neural network (DNN) based SLP framework. Instead of naively training a DNN architecture for SLP without considering the specifics of the optimization objective of the SLP domain, our proposal unfolds a power minimization SLP formulation based on the interior point method (IPM) proximal ‘log’ barrier function. Furthermore, we extend our proposal to a robust precoding design under channel state information (CSI) uncertainty. The results show that our proposed learning framework provides near-optimal performance while reducing the computational cost from O(n7.5) to O(n3) for the symmetrical system case where n=numberoftransmitantennas=numberofusers. This significant complexity reduction is also reflected in a proportional decrease in the proposed approach’s execution time compared to the SLP optimization-based solution.
- 28 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 4, 1075-1090
Open AccessAn Unsupervised Deep Unfolding Framework for Robust Symbol-Level Precoding
Symbol Level Precoding (SLP) has attracted significant research interest due to its ability to exploit interference for energy-efficient transmission. This paper proposes an unsupervised deep-neural network (DNN) based SLP framework. Instead of naively training a DNN architecture for SLP without considering the specifics of the optimization objective of the SLP domain, our proposal unfolds a power minimization SLP formulation based on the interior point method (IPM) proximal ‘log’ barrier function. Furthermore, we extend our proposal to a robust precoding design under channel state information (CSI) uncertainty. The results show that our proposed learning framework provides near-optimal performance while reducing the computational cost from O(n7.5) to O(n3) for the symmetrical system case where n=numberoftransmitantennas=numberofusers. This significant complexity reduction is also reflected in a proportional decrease in the proposed approach’s execution time compared to the SLP optimization-based solution.
- Open Access
An Unsupervised Learning-Based Approach for Symbol-Level-Precoding
This paper proposes an unsupervised learning-based precoding framework that trains deep neural networks (DNNs) with no target labels by unfolding an interior point method (IPM) proximal `log' barrier function. The proximal `log' barrier function is derived from the strict power minimization formulation subject to signal-to-interference-plus-noise ratio (SINR) constraint. The proposed scheme exploits the known interference via symbol-level precoding (SLP) to minimize the transmit power and is named strict Symbol-Level-Precoding deep network (SLP-SDNet). The results show that SLP-SDNet outperforms the conventional block-level-precoding (Conventional BLP) scheme while achieving near-optimal performance faster than the SLP optimization-based approach.
Open AccessAn Unsupervised Learning-Based Approach for Symbol-Level-Precoding
This paper proposes an unsupervised learning-based precoding framework that trains deep neural networks (DNNs) with no target labels by unfolding an interior point method (IPM) proximal `log' barrier function. The proximal `log' barrier function is derived from the strict power minimization formulation subject to signal-to-interference-plus-noise ratio (SINR) constraint. The proposed scheme exploits the known interference via symbol-level precoding (SLP) to minimize the transmit power and is named strict Symbol-Level-Precoding deep network (SLP-SDNet). The results show that SLP-SDNet outperforms the conventional block-level-precoding (Conventional BLP) scheme while achieving near-optimal performance faster than the SLP optimization-based approach.
- 1 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (3) , 1578-1591
Sequence-Level Reference Frames in Video Coding
The proliferation of low-cost DRAM chipsets now begins to allow for the consideration of substantially-increased decoded picture buffers in advanced video coding standards such as HEVC, VVC, and Google VP9. At the same time, the increasing demand for rapid scene changes and multiple scene repetitions in entertainment or broadcast content indicates that extending the frame referencing interval to tens of minutes or even the entire video sequence may offer coding gains, as long as one is able to identify frame similarity in a computationally- and memory-efficient manner. Motivated by these observations, we propose a “stitching” method that defines a reference buffer and a reference frame selection algorithm. Our proposal extends the referencing interval of inter-frame video coding to the entire length of video sequences. Our reference frame selection algorithm uses well-established feature descriptor methods that describe frame structural elements in a compact and semantically-rich manner. We propose to combine such compact descriptors with a similarity scoring mechanism in order to select the frames to be “stitched” to reference picture buffers of advanced inter-frame encoders like HEVC, VVC, and VP9 without breaking standard compliance. Our evaluation on synthetic and real-world video sequences with the HEVC and VVC reference encoders shows that our method offers significant rate gains, with complexity and memory requirements that remain manageable for practical encoders and decoders.
- 1 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (3) , 1578-1591
Sequence-Level Reference Frames in Video Coding
The proliferation of low-cost DRAM chipsets now begins to allow for the consideration of substantially-increased decoded picture buffers in advanced video coding standards such as HEVC, VVC, and Google VP9. At the same time, the increasing demand for rapid scene changes and multiple scene repetitions in entertainment or broadcast content indicates that extending the frame referencing interval to tens of minutes or even the entire video sequence may offer coding gains, as long as one is able to identify frame similarity in a computationally- and memory-efficient manner. Motivated by these observations, we propose a “stitching” method that defines a reference buffer and a reference frame selection algorithm. Our proposal extends the referencing interval of inter-frame video coding to the entire length of video sequences. Our reference frame selection algorithm uses well-established feature descriptor methods that describe frame structural elements in a compact and semantically-rich manner. We propose to combine such compact descriptors with a similarity scoring mechanism in order to select the frames to be “stitched” to reference picture buffers of advanced inter-frame encoders like HEVC, VVC, and VP9 without breaking standard compliance. Our evaluation on synthetic and real-world video sequences with the HEVC and VVC reference encoders shows that our method offers significant rate gains, with complexity and memory requirements that remain manageable for practical encoders and decoders.
- 17 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 9084-9098
Graph-Based Spatio-Temporal Feature Learning for Neuromorphic Vision Sensing
Neuromorphic vision sensing (NVS) devices represent visual information as sequences of asynchronous discrete events (a.k.a., “spikes”) in response to changes in scene reflectance. Unlike conventional active pixel sensing (APS), NVS allows for significantly higher event sampling rates at substantially increased energy efficiency and robustness to illumination changes. However, feature representation for NVS is far behind its APS-based counterparts, resulting in lower performance in high-level computer vision tasks. To fully utilize its sparse and asynchronous nature, we propose a compact graph representation for NVS, which allows for end-to-end learning with graph convolution neural networks. We couple this with a novel end-to-end feature learning framework that accommodates both appearancebased and motion-based tasks. The core of our framework comprises a spatial feature learning module, which utilizes residual-graph convolutional neural networks (RG-CNN), for end-to-end learning of appearance-based features directly from graphs. We extend this with our proposed Graph2Grid block and temporal feature learning module for efficiently modelling temporal dependencies over multiple graphs and a long temporal extent. We show how our framework can be configured for object classification, action recognition and action similarity labeling. Importantly, our approach preserves the spatial and temporal coherence of spike events, while requiring less computation and memory. The experimental validation shows that our proposed framework outperforms all recent methods on standard datasets. Finally, to address the absence of large real-world NVS datasets for complex recognition tasks, we introduce, evaluate and make available the American Sign Language letters (ASL-DVS), as well as human action dataset (UCF101-DVS, HMDB51-DVS and ASLAN-DVS).
- 17 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 9084-9098
Graph-Based Spatio-Temporal Feature Learning for Neuromorphic Vision Sensing
Neuromorphic vision sensing (NVS) devices represent visual information as sequences of asynchronous discrete events (a.k.a., “spikes”) in response to changes in scene reflectance. Unlike conventional active pixel sensing (APS), NVS allows for significantly higher event sampling rates at substantially increased energy efficiency and robustness to illumination changes. However, feature representation for NVS is far behind its APS-based counterparts, resulting in lower performance in high-level computer vision tasks. To fully utilize its sparse and asynchronous nature, we propose a compact graph representation for NVS, which allows for end-to-end learning with graph convolution neural networks. We couple this with a novel end-to-end feature learning framework that accommodates both appearancebased and motion-based tasks. The core of our framework comprises a spatial feature learning module, which utilizes residual-graph convolutional neural networks (RG-CNN), for end-to-end learning of appearance-based features directly from graphs. We extend this with our proposed Graph2Grid block and temporal feature learning module for efficiently modelling temporal dependencies over multiple graphs and a long temporal extent. We show how our framework can be configured for object classification, action recognition and action similarity labeling. Importantly, our approach preserves the spatial and temporal coherence of spike events, while requiring less computation and memory. The experimental validation shows that our proposed framework outperforms all recent methods on standard datasets. Finally, to address the absence of large real-world NVS datasets for complex recognition tasks, we introduce, evaluate and make available the American Sign Language letters (ASL-DVS), as well as human action dataset (UCF101-DVS, HMDB51-DVS and ASLAN-DVS).
- Open Access
Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem.To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.
Open AccessBiased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem.To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.
- 7 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 68 (10) , 6101-6113
Complexity-Scalable Neural-Network-Based MIMO Detection With Learnable Weight Scaling
This paper introduces a framework for systematic complexity scaling of deep neural network (DNN) based MIMO detectors. The model uses a fraction of the DNN inputs by scaling their values through weights that follow monotonically non-increasing functions. This allows for weight scaling across and within the different DNN layers in order to achieve accuracy-vs.-complexity scalability during inference. In order to further improve the performance of our proposal, we introduce a sparsity-inducing regularization constraint in conjunction with trainable weight-scaling functions. In this way, the network learns to balance detection accuracy versus complexity while also increasing robustness to changes in the activation patterns, leading to further improvement in the detection accuracy and BER performance at the same inference complexity. Numerical results show that our approach is 10-fold and 100-fold less complex than classical approaches based on semi-definite relaxation and ML detection, respectively.
- 7 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 68 (10) , 6101-6113
Complexity-Scalable Neural-Network-Based MIMO Detection With Learnable Weight Scaling
This paper introduces a framework for systematic complexity scaling of deep neural network (DNN) based MIMO detectors. The model uses a fraction of the DNN inputs by scaling their values through weights that follow monotonically non-increasing functions. This allows for weight scaling across and within the different DNN layers in order to achieve accuracy-vs.-complexity scalability during inference. In order to further improve the performance of our proposal, we introduce a sparsity-inducing regularization constraint in conjunction with trainable weight-scaling functions. In this way, the network learns to balance detection accuracy versus complexity while also increasing robustness to changes in the activation patterns, leading to further improvement in the detection accuracy and BER performance at the same inference complexity. Numerical results show that our approach is 10-fold and 100-fold less complex than classical approaches based on semi-definite relaxation and ML detection, respectively.
- 3 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 7656-7667
Biased Mixtures of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem. To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.
- 3 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 7656-7667
Biased Mixtures of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem. To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.
- Open Access
Complexity-Scalable Neural Network Based MIMO Detection With Learnable Weight Scaling
This paper introduces a framework for systematic complexity scaling of deep neural network(DNN) based MIMO detectors. The model uses a fraction of the DNN inputs by scaling their values through weights that follow monotonically non-increasing functions. This allows for weight scaling across and within the different DNN layers in order to achieve accuracy-vs.-complexity scalability during inference. In order to further improve the performance of our proposal, we introduce a sparsity-inducing regularization constraint in conjunction with trainable weight-scaling functions. In this way, the network learns to balance detection accuracy versus complexity while also increasing robustness to changes in the activation patterns, leading to further improvement in the detection accuracy and BER performance at the same inference complexity. Numerical results show that our approach is 10-foldand 100-fold less complex than classical approaches based on semi-definite relaxation and ML detection, respectively.
Open AccessComplexity-Scalable Neural Network Based MIMO Detection With Learnable Weight Scaling
This paper introduces a framework for systematic complexity scaling of deep neural network(DNN) based MIMO detectors. The model uses a fraction of the DNN inputs by scaling their values through weights that follow monotonically non-increasing functions. This allows for weight scaling across and within the different DNN layers in order to achieve accuracy-vs.-complexity scalability during inference. In order to further improve the performance of our proposal, we introduce a sparsity-inducing regularization constraint in conjunction with trainable weight-scaling functions. In this way, the network learns to balance detection accuracy versus complexity while also increasing robustness to changes in the activation patterns, leading to further improvement in the detection accuracy and BER performance at the same inference complexity. Numerical results show that our approach is 10-foldand 100-fold less complex than classical approaches based on semi-definite relaxation and ML detection, respectively.
- 16 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 30 (12) , 4913-4928
Deep Video Precoding
Several groups worldwide are currently investigating how deep learning may advance the state-of-the-art in image and video coding. An open question is how to make deep neural networks work in conjunction with existing (and upcoming) video codecs, such as MPEG H.264/AVC, H.265/HEVC, VVC, Google VP9 and AOMedia AV1, AV2, as well as existing container and transport formats, without imposing any changes at the client side. Such compatibility is a crucial aspect when it comes to practical deployment, especially when considering the fact that the video content industry and hardware manufacturers are expected to remain committed to supporting these standards for the foreseeable future. We propose to use deep neural networks as precoders for current and future video codecs and adaptive video streaming systems. In our current design, the core precoding component comprises a cascaded structure of downscaling neural networks that operates during video encoding, prior to transmission. This is coupled with a precoding mode selection algorithm for each independently-decodable stream segment, which adjusts the downscaling factor according to scene characteristics, the utilized encoder, and the desired bitrate and encoding configuration. Our framework is compatible with all current and future codec and transport standards, as our deep precoding network structure is trained in conjunction with linear upscaling filters (e.g., the bilinear filter), which are supported by all web video players. Extensive evaluation on FHD (1080p) and UHD (2160p) content and with widely-used H.264/AVC, H.265/HEVC and VP9 encoders, as well as a preliminary evaluation with the current test model of VVC (v.6.2rc1), shows that coupling such standards with the proposed deep video precoding allows for 8% to 52% rate reduction under encoding configurations and bitrates suitable for video-on-demand adaptive streaming systems. The use of precoding can also lead to encoding complexity reduction, which is essential for cost-effective cloud deployment of complex encoders like H.265/HEVC, VP9 and VVC, especially when considering the prominence of high-resolution adaptive video streaming.
- 16 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 30 (12) , 4913-4928
Deep Video Precoding
Several groups worldwide are currently investigating how deep learning may advance the state-of-the-art in image and video coding. An open question is how to make deep neural networks work in conjunction with existing (and upcoming) video codecs, such as MPEG H.264/AVC, H.265/HEVC, VVC, Google VP9 and AOMedia AV1, AV2, as well as existing container and transport formats, without imposing any changes at the client side. Such compatibility is a crucial aspect when it comes to practical deployment, especially when considering the fact that the video content industry and hardware manufacturers are expected to remain committed to supporting these standards for the foreseeable future. We propose to use deep neural networks as precoders for current and future video codecs and adaptive video streaming systems. In our current design, the core precoding component comprises a cascaded structure of downscaling neural networks that operates during video encoding, prior to transmission. This is coupled with a precoding mode selection algorithm for each independently-decodable stream segment, which adjusts the downscaling factor according to scene characteristics, the utilized encoder, and the desired bitrate and encoding configuration. Our framework is compatible with all current and future codec and transport standards, as our deep precoding network structure is trained in conjunction with linear upscaling filters (e.g., the bilinear filter), which are supported by all web video players. Extensive evaluation on FHD (1080p) and UHD (2160p) content and with widely-used H.264/AVC, H.265/HEVC and VP9 encoders, as well as a preliminary evaluation with the current test model of VVC (v.6.2rc1), shows that coupling such standards with the proposed deep video precoding allows for 8% to 52% rate reduction under encoding configurations and bitrates suitable for video-on-demand adaptive streaming systems. The use of precoding can also lead to encoding complexity reduction, which is essential for cost-effective cloud deployment of complex encoders like H.265/HEVC, VP9 and VVC, especially when considering the prominence of high-resolution adaptive video streaming.