Pose-variant 3D Facial Attribute Generation

/in /by

We address the challenging problem of generating facial attributes using a single image in an unconstrained pose. In contrast to prior works that largely consider generation on 2D near-frontal images, we propose a GAN-based framework to generate attributes directly on a dense 3D representation given by UV texture and position maps, resulting in photorealistic, geometrically-consistent and identity-preserving outputs. Starting from a self-occluded UV texture map obtained by applying an off-the-shelf 3D reconstruction method, we propose two novel components. First, a texture completion generative adversarial network (TC-GAN) completes the partial UV texture map. Second, a 3D attribute generation GAN (3DA-GAN) synthesizes the target attribute while obtaining an appearance consistent with 3D face geometry and preserving identity. Extensive experiments on CelebA, LFW and IJB-A show that our method achieves consistently better attribute generation accuracy than prior methods, a higher degree of qualitative photorealism and preserves face identity information.

Read more

Size and Alignment Independent Classification of the High-order Spatial Modes of a Light Beam Using a Convolutional Neural Network

/in /by

The higher-order spatial modes of a light beam are receiving significant interest. They can be used to further increase the data speeds of high speed optical communication, and for novel optical sensing modalities. As such, the classification of higher-order spatial modes is ubiquitous. Canonical classification methods typically require the use of unconventional optical devices. However, in addition to having prohibitive cost, complexity, and efficacy, such methods are dependent on the light beam’s size and alignment. In this work, a novel method to classify higher-order spatial modes is presented, where a convolutional neural network is applied to images of higher-order spatial modes that are taken with a conventional camera. In contrast to previous methods, by training the convolutional neural network with higher-order spatial modes of various alignments and sizes, this method is not dependent on the light beam’s size and alignment. As a proof of principle, images of 4 Hermite-Gaussian modes (HG00, HG01, HG10, and HG11) are numerically calculated via known solutions to the electromagnetic wave equation, and used to synthesize training examples. It is shown that as compared to training the convolutional neural network with training examples that have the same sizes and alignments, a?~2×?increase in accuracy can be achieved.

Read more

Field and lab experimental demonstration of nonlinear impairment compensation using neural networks

/in /by

Fiber nonlinearity is one of the major limitations to the achievable capacity in long distance fiber optic transmission systems. Nonlinear impairments are determined by the signal pattern and the transmission system parameters. Deterministic algorithms based on approximating the nonlinear Schrodinger equation through digital back propagation, or a single step approach based on perturbation methods have been demonstrated, however, their implementation demands excessive signal processing resources, and accurate knowledge of the transmission system. A completely different approach uses machine learning algorithms to learn from the received data itself to figure out the nonlinear impairment. In this work, a single-step, system agnostic nonlinearity compensation algorithm based on a neural network is proposed to pre-distort symbols at transmitter side to demonstrate ~0.6?dB Q improvement after 2800?km standard single-mode fiber transmission using 32 Gbaud signal. Without prior knowledge of the transmission system, the neural network tensor weights are constructed from training data thanks to the intra-channel cross-phase modulation and intra-channel four-wave mixing triplets used as input features.

Read more

Decentralized Transactive Energy Auctions with Bandit Learning

/in /by

The power systems worldwide have been embracing the rapid growth of distributed energy resources. Commonly, distributed energy resources exist in the distribution level, such as electric vehicles, rooftop photovoltaic panels, and home battery systems, which cannot be controlled by a centralized entity like a utility. However, a large number of distributed energy resources have potential to reshape the power generation landscape when the owners (prosumers) are allowed to send electricity back to the grids. Transactive energy paradigms are emerging for orchestrating the coordination of prosumers and consumers by enabling the exchange of energy among them. In this paper, we propose a transactive energy auction framework based on blockchain technology for creating trustworthy and transparent transactive environments in distribution networks, which does not rely on a centralized entity to clear transactions. Moreover, we propose intelligent decentralized decision-making strategies by bandit learning for market participants to locally decide their energy prices in auctions. The bandit learning approach can provide market participants with more benefits under the blockchain framework than trading energy with the centralized entity, which is further supported by the preliminary simulated results conducted over our blockchain-based platform.

Read more

Neural-Network-Based G-OSNR Estimation of Probabilistic-Shaped 144QAM Channels in DWDM Metro Network Field Trial

/in /by

A two-stage neural network model is applied on captured PS-144QAM raw data to estimate channel G-OSNR in a metro network field trial. We obtained 0.27dB RMSE with first-stage CNN classifier and second-stage ANN regressions.

Read more

Energy Predictive Models with Limited Data using Transfer Learning

/in /by

In this paper, we consider the problem of developing predictive models with limited data for energy assets such as electricity loads, PV power generations, etc. We specifically investigate the cases where the amount of historical data is not sufficient to effectively train the prediction model. We first develop an energy predictive model based on convolutional neural network (CNN) which is well suited to capture the interaday, daily, and weekly cyclostationary patterns, trends and seasonalities in energy assets time series. A transfer learning strategy is then proposed to address the challenge of limited training data. We demonstrate our approach on a usecase of daily electricity demand forecasting. we show practicing the transfer learning strategy on the CNN model results in significant improvement to existing forecasting methods.

Read more

Clairvoyant Networks

/in /by

We use the term clairvoyant to refer to networks that provide on-demand visibility for any flow at any time. Traditionally, network visibility is achieved by instrumenting and passively monitoring all flows in a network. SDN networks, by design endowed with full visibility, offer another alternative to network-wide flow monitoring. Both approaches incur significant capital and operational costs to make networks clairvoyant. In this paper, we argue that we can make any existing network clairvoyant by installing one or more SDN-enabled switches and a specialized controller to support on-demand visibility. We analyze the benefits and costs of such clairvoyant networks and provide a basic design by integrating two existing mechanisms for updating paths through legacy switches with SDN, telekinesis and magnet MACs. Our evaluation on a lab testbed and through extensive simulations show that, even with a single SDN-enabled switch, operators can make any flow visible for monitoring within milliseconds, albeit at 38% average increase in path length. With as many as 2% strategically chosen legacy switches replaced with SDN switches, clairvoyant networks achieve on-demand flow visibility with negligible overhead.

Read more

A Dataset for High-Level 3D Scene Understanding of Complex Road Scenes in the Top-View

/in /by

We introduce a novel dataset for high-level 3D scene understanding of complex road scenes. Our annotations extend the existing datasets KITTI [5] and nuScenes [1] with semantically and geometrically meaningful attributes like the number of lanes or the existence of, and distance to, intersections, sidewalks and crosswalks. Our attributes are rich enough to build a meaningful representation of the scene in the top-view and provide a tangible interface to the real world for several practical applications.

Read more

A Parametric Top-View Representation of Complex Road Scenes

/in /by

In this paper, we address the problem of inferring the layout of complex road scenes given a single camera as input. To achieve that, we first propose a novel parameterized model of road layouts in a top-view representation, which is not only intuitive for human visualization but also provides an interpretable interface for higher-level decision making. Moreover, the design of our top-view scene model allows for efficient sampling and thus generation of large-scale simulated data, which we leverage to train a deep neural network to infer our scene model’s parameters. Specifically, our proposed training procedure uses supervised domain-adaptation techniques to incorporate both simulated as well as manually annotated data. Finally, we design a Conditional Random Field (CRF) that enforces coherent predictions for a single frame and encourages temporal smoothness among video frames. Experiments on two public data sets show that: (1) Our parametric top-view model is representative enough to describe complex road scenes; (2) The proposed method outperforms baselines trained on manually-annotated or simulated data only, thus getting the best of both; (3) Our CRF is able to generate temporally smoothed while semantically meaningful results.

Read more

Feature Transfer Learning for Face Recognition with Under-Represented Data

/in /by

Despite the large volume of face recognition datasets, there is a significant portion of subjects, of which the samples are insufficient and thus under-represented. Ignoring such significant portion results in insufficient training data. Training with under-represented data leads to biased classifiers in conventionally-trained deep networks. In this paper, we propose a center-based feature transfer framework to augment the feature space of under-represented subjects from the regular subjects that have sufficiently diverse samples. A Gaussian prior of the variance is assumed across all subjects and the variance from regular ones are transferred to the under-represented ones. This encourages the under-represented distribution to be closer to the regular distribution. Further, an alternating training regimen is proposed to simultaneously achieve less biased classifiers and a more discriminative feature representation. We conduct ablative study to mimic the under-represented datasets by varying the portion of under-represented classes on the MS-Celeb-1M dataset. Advantageous results on LFW, IJB-A and MS-Celeb-1M demonstrate the effectiveness of our feature transfer and training strategy, compared to both general baselines and state-of-the-art methods. Moreover, our feature transfer successfully presents smooth visual interpolation, which conducts disentanglement to preserve identity of a class while augmenting its feature space with non-identity variations such as pose and lighting.

Read more