Paper Group ANR 941
CNNs Fusion for Building Detection in Aerial Images for the Building Detection Challenge. Enhanced Machine Learning Techniques for Early HARQ Feedback Prediction in 5G. Binary output layer of feedforward neural networks for solving multi-class classification problems. Optimizing Variational Quantum Circuits using Evolution Strategies. Dropout durin …
CNNs Fusion for Building Detection in Aerial Images for the Building Detection Challenge
| Title | CNNs Fusion for Building Detection in Aerial Images for the Building Detection Challenge |
| Authors | Rémi Delassus, Romain Giot |
| Abstract | This paper presents our contribution to the DeepGlobe Building Detection Challenge. We enhanced the SpaceNet Challenge winning solution by proposing a new fusion strategy based on a deep combiner using segmentation both results of different CNN and input data to segment. Segmentation results for all cities have been significantly improved (between 1% improvement over the baseline for the smallest one to more than 7% for the largest one). The separation of adjacent buildings should be the next enhancement made to the solution. |
| Tasks | |
| Published | 2018-09-28 |
| URL | http://arxiv.org/abs/1809.10976v1 |
| http://arxiv.org/pdf/1809.10976v1.pdf | |
| PWC | https://paperswithcode.com/paper/cnns-fusion-for-building-detection-in-aerial |
| Repo | |
| Framework | |
Enhanced Machine Learning Techniques for Early HARQ Feedback Prediction in 5G
| Title | Enhanced Machine Learning Techniques for Early HARQ Feedback Prediction in 5G |
| Authors | Nils Strodthoff, Barış Göktepe, Thomas Schierl, Cornelius Hellge, Wojciech Samek |
| Abstract | We investigate Early Hybrid Automatic Repeat reQuest (E-HARQ) feedback schemes enhanced by machine learning techniques as a path towards ultra-reliable and low-latency communication (URLLC). To this end, we propose machine learning methods to predict the outcome of the decoding process ahead of the end of the transmission. We discuss different input features and classification algorithms ranging from traditional methods to newly developed supervised autoencoders. These methods are evaluated based on their prospects of complying with the URLLC requirements of effective block error rates below $10^{-5}$ at small latency overheads. We provide realistic performance estimates in a system model incorporating scheduling effects to demonstrate the feasibility of E-HARQ across different signal-to-noise ratios, subcode lengths, channel conditions and system loads, and show the benefit over regular HARQ and existing E-HARQ schemes without machine learning. |
| Tasks | |
| Published | 2018-07-27 |
| URL | https://arxiv.org/abs/1807.10495v2 |
| https://arxiv.org/pdf/1807.10495v2.pdf | |
| PWC | https://paperswithcode.com/paper/enhanced-machine-learning-techniques-for |
| Repo | |
| Framework | |
Binary output layer of feedforward neural networks for solving multi-class classification problems
| Title | Binary output layer of feedforward neural networks for solving multi-class classification problems |
| Authors | Sibo Yang, Chao Zhang, Wei Wu |
| Abstract | Considered in this short note is the design of output layer nodes of feedforward neural networks for solving multi-class classification problems with r (bigger than or equal to 3) classes of samples. The common and conventional setting of output layer, called “one-to-one approach” in this paper, is as follows: The output layer contains r output nodes corresponding to the r classes. And for an input sample of the i-th class, the ideal output is 1 for the i-th output node, and 0 for all the other output nodes. We propose in this paper a new “binary approach”: Suppose r is (2^(q minus 1), 2^q] with q bigger than or equal to 2, then we let the output layer contain q output nodes, and let the ideal outputs for the r classes be designed in a binary manner. Numerical experiments carried out in this paper show that our binary approach does equally good job as, but uses less output nodes than, the traditional one-to-one approach. |
| Tasks | |
| Published | 2018-01-22 |
| URL | http://arxiv.org/abs/1801.07599v1 |
| http://arxiv.org/pdf/1801.07599v1.pdf | |
| PWC | https://paperswithcode.com/paper/binary-output-layer-of-feedforward-neural |
| Repo | |
| Framework | |
Optimizing Variational Quantum Circuits using Evolution Strategies
| Title | Optimizing Variational Quantum Circuits using Evolution Strategies |
| Authors | Johannes S. Otterbach |
| Abstract | This version withdrawn by arXiv administrators because the submitter did not have the right to agree to our license at the time of submission. |
| Tasks | |
| Published | 2018-06-12 |
| URL | http://arxiv.org/abs/1806.04344v1 |
| http://arxiv.org/pdf/1806.04344v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-variational-quantum-circuits-using |
| Repo | |
| Framework | |
Dropout during inference as a model for neurological degeneration in an image captioning network
| Title | Dropout during inference as a model for neurological degeneration in an image captioning network |
| Authors | Bai Li, Ran Zhang, Frank Rudzicz |
| Abstract | We replicate a variation of the image captioning architecture by Vinyals et al. (2015), then introduce dropout during inference mode to simulate the effects of neurodegenerative diseases like Alzheimer’s disease (AD) and Wernicke’s aphasia (WA). We evaluate the effects of dropout on language production by measuring the KL-divergence of word frequency distributions and other linguistic metrics as dropout is added. We find that the generated sentences most closely approximate the word frequency distribution of the training corpus when using a moderate dropout of 0.4 during inference. |
| Tasks | Image Captioning |
| Published | 2018-08-11 |
| URL | http://arxiv.org/abs/1808.03747v1 |
| http://arxiv.org/pdf/1808.03747v1.pdf | |
| PWC | https://paperswithcode.com/paper/dropout-during-inference-as-a-model-for |
| Repo | |
| Framework | |
Disaster Monitoring using Unmanned Aerial Vehicles and Deep Learning
| Title | Disaster Monitoring using Unmanned Aerial Vehicles and Deep Learning |
| Authors | Andreas Kamilaris, Francesc X. Prenafeta-Boldú |
| Abstract | Monitoring of disasters is crucial for mitigating their effects on the environment and human population, and can be facilitated by the use of unmanned aerial vehicles (UAV), equipped with camera sensors that produce aerial photos of the areas of interest. A modern technique for recognition of events based on aerial photos is deep learning. In this paper, we present the state of the art work related to the use of deep learning techniques for disaster identification. We demonstrate the potential of this technique in identifying disasters with high accuracy, by means of a relatively simple deep learning model. Based on a dataset of 544 images (containing disaster images such as fires, earthquakes, collapsed buildings, tsunami and flooding, as well as non-disaster scenes), our results show an accuracy of 91% achieved, indicating that deep learning, combined with UAV equipped with camera sensors, have the potential to predict disasters with high accuracy. |
| Tasks | |
| Published | 2018-07-31 |
| URL | http://arxiv.org/abs/1807.11805v2 |
| http://arxiv.org/pdf/1807.11805v2.pdf | |
| PWC | https://paperswithcode.com/paper/disaster-monitoring-using-unmanned-aerial |
| Repo | |
| Framework | |
Collaborative Pressure Ulcer Prevention: An Automated Skin Damage and Pressure Ulcer Assessment Tool for Nursing Professionals, Patients, Family Members and Carers
| Title | Collaborative Pressure Ulcer Prevention: An Automated Skin Damage and Pressure Ulcer Assessment Tool for Nursing Professionals, Patients, Family Members and Carers |
| Authors | Paul Fergus, Carl Chalmers, David Tully |
| Abstract | This paper describes the Pressure Ulcers Online Website, which is a first step solution towards a new and innovative platform for helping people to detect, understand and manage pressure ulcers. It outlines the reasons why the project has been developed and provides a central point of contact for pressure ulcer analysis and ongoing research. Using state-of-the-art technologies in convolutional neural networks and transfer learning along with end-to-end web technologies, this platform allows pressure ulcers to be analysed and findings to be reported. As the system evolves through collaborative partnerships, future versions will provide decision support functions to describe the complex characteristics of pressure ulcers along with information on wound care across multiple user boundaries. This project is therefore intended to raise awareness and support for people suffering with or providing care for pressure ulcers. |
| Tasks | Transfer Learning |
| Published | 2018-08-17 |
| URL | http://arxiv.org/abs/1808.06503v1 |
| http://arxiv.org/pdf/1808.06503v1.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-pressure-ulcer-prevention-an |
| Repo | |
| Framework | |
Competitive caching with machine learned advice
| Title | Competitive caching with machine learned advice |
| Authors | Thodoris Lykouris, Sergei Vassilvitskii |
| Abstract | Traditional online algorithms encapsulate decision making under uncertainty, and give ways to hedge against all possible future events, while guaranteeing a nearly optimal solution as compared to an offline optimum. On the other hand, machine learning algorithms are in the business of extrapolating patterns found in the data to predict the future, and usually come with strong guarantees on the expected generalization error. In this work we develop a framework for augmenting online algorithms with a machine learned oracle to achieve competitive ratios that provably improve upon unconditional worst case lower bounds when the oracle has low error. Our approach treats the oracle as a complete black box, and is not dependent on its inner workings, or the exact distribution of its errors. We apply this framework to the traditional caching problem – creating an eviction strategy for a cache of size $k$. We demonstrate that naively following the oracle’s recommendations may lead to very poor performance, even when the average error is quite low. Instead we show how to modify the Marker algorithm to take into account the oracle’s predictions, and prove that this combined approach achieves a competitive ratio that both (i) decreases as the oracle’s error decreases, and (ii) is always capped by $O(\log k)$, which can be achieved without any oracle input. We complement our results with an empirical evaluation of our algorithm on real world datasets, and show that it performs well empirically even using simple off-the-shelf predictions. |
| Tasks | Decision Making, Decision Making Under Uncertainty |
| Published | 2018-02-15 |
| URL | https://arxiv.org/abs/1802.05399v3 |
| https://arxiv.org/pdf/1802.05399v3.pdf | |
| PWC | https://paperswithcode.com/paper/competitive-caching-with-machine-learned |
| Repo | |
| Framework | |
Unsupervised Change Detection in Satellite Images Using Convolutional Neural Networks
| Title | Unsupervised Change Detection in Satellite Images Using Convolutional Neural Networks |
| Authors | Kevin Louis de Jong, Anna Sergeevna Bosman |
| Abstract | This paper proposes an efficient unsupervised method for detecting relevant changes between two temporally different images of the same scene. A convolutional neural network (CNN) for semantic segmentation is implemented to extract compressed image features, as well as to classify the detected changes into the correct semantic classes. A difference image is created using the feature map information generated by the CNN, without explicitly training on target difference images. Thus, the proposed change detection method is unsupervised, and can be performed using any CNN model pre-trained for semantic segmentation. |
| Tasks | Semantic Segmentation |
| Published | 2018-12-14 |
| URL | http://arxiv.org/abs/1812.05815v2 |
| http://arxiv.org/pdf/1812.05815v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-change-detection-in-satellite |
| Repo | |
| Framework | |
SpiderBoost: A Class of Faster Variance-reduced Algorithms for Nonconvex Optimization
| Title | SpiderBoost: A Class of Faster Variance-reduced Algorithms for Nonconvex Optimization |
| Authors | Zhe Wang, Kaiyi Ji, Yi Zhou, Yingbin Liang, Vahid Tarokh |
| Abstract | There has been extensive research on developing stochastic variance reduced methods to solve large-scale optimization problems. More recently, novel algorithms SARAH \citep{Lam2017a,Lam2017b} and SPIDER \citep{Fang2018} of such a type have been developed. In particular, SPIDER has been shown in \cite{Fang2018} to outperform existing algorithms of the same type and meet the lower bound in certain regimes for nonconvex optimization. Though appealing in theory, SPIDER requires $\epsilon$-level stepsize to guarantee the convergence, and consequently runs slow in practice. This paper proposes SpiderBoost as an improved scheme, which comes with two major advantages compared to SPIDER. First, it allows much larger stepsize without sacrificing the convergence rate, and hence runs substantially faster in practice. Second, it extends much more easily to proximal algorithms with guaranteed convergence for solving composite optimization problems, which appears challenging for SPIDER due to stringent requirement on per-iteration increment to guarantee its convergence. Both advantages can be attributed to the new convergence analysis we develop for SpiderBoost that allows much more flexibility for choosing algorithm parameters. As further generalization of SpiderBoost, we show that proximal SpiderBoost achieves a stochastic first-order oracle (SFO) complexity of $\mathcal{O}(\min {n^{1/2}\epsilon^{-2},\epsilon^{-3}})$ for composite optimization, which improves the existing best results by a factor of $\mathcal{O}(\min{n^{1/6},\epsilon^{-1/3}})$. Moreover, for nonconvex optimization under the gradient dominance condition and in an online setting, we also obtain improved oracle complexity results compared to the corresponding state-of-the-art results. |
| Tasks | |
| Published | 2018-10-25 |
| URL | http://arxiv.org/abs/1810.10690v2 |
| http://arxiv.org/pdf/1810.10690v2.pdf | |
| PWC | https://paperswithcode.com/paper/spiderboost-a-class-of-faster-variance |
| Repo | |
| Framework | |
HybridNet: Integrating Model-based and Data-driven Learning to Predict Evolution of Dynamical Systems
| Title | HybridNet: Integrating Model-based and Data-driven Learning to Predict Evolution of Dynamical Systems |
| Authors | Yun Long, Xueyuan She, Saibal Mukhopadhyay |
| Abstract | The robotic systems continuously interact with complex dynamical systems in the physical world. Reliable predictions of spatiotemporal evolution of these dynamical systems, with limited knowledge of system dynamics, are crucial for autonomous operation. In this paper, we present HybridNet, a framework that integrates data-driven deep learning and model-driven computation to reliably predict spatiotemporal evolution of a dynamical systems even with in-exact knowledge of their parameters. A data-driven deep neural network (DNN) with Convolutional LSTM (ConvLSTM) as the backbone is employed to predict the time-varying evolution of the external forces/perturbations. On the other hand, the model-driven computation is performed using Cellular Neural Network (CeNN), a neuro-inspired algorithm to model dynamical systems defined by coupled partial differential equations (PDEs). CeNN converts the intricate numerical computation into a series of convolution operations, enabling a trainable PDE solver. With a feedback control loop, HybridNet can learn the physical parameters governing the system’s dynamics in real-time, and accordingly adapt the computation models to enhance prediction accuracy for time-evolving dynamical systems. The experimental results on two dynamical systems, namely, heat convection-diffusion system, and fluid dynamical system, demonstrate that the HybridNet produces higher accuracy than the state-of-the-art deep learning based approach. |
| Tasks | |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07439v2 |
| http://arxiv.org/pdf/1806.07439v2.pdf | |
| PWC | https://paperswithcode.com/paper/hybridnet-integrating-model-based-and-data |
| Repo | |
| Framework | |
A novel particle swarm optimizer with multi-stage transformation and genetic operation for VLSI routing
| Title | A novel particle swarm optimizer with multi-stage transformation and genetic operation for VLSI routing |
| Authors | Genggeng Liu, Zhen Zhuang, Wenzhong Guo, Naixue Xiong, Guolong Chen |
| Abstract | As the basic model for very large scale integration (VLSI) routing, the Steiner minimal tree (SMT) can be used in various practical problems, such as wire length optimization, congestion, and time delay estimation. In this paper, a novel particle swarm optimization (PSO) algorithm based on multi-stage transformation and genetic operation is presented to construct two types of SMT, including non-Manhattan SMT and Manhattan SMT. Firstly, in order to be able to handle two types of SMT problems at the same time, an effective edge-vertex encoding strategy is proposed. Secondly, a multi-stage transformation strategy is proposed to both expand the algorithm search space and ensure the effective convergence. We have tested three types from two to four stages and various combinations under each type to highlight the best combination. Thirdly, the genetic operators combined with union-find partition are designed to construct the discrete particle update formula for discrete VLSI routing. Moreover, in order to introduce uncertainty and diversity into the search of PSO algorithm, we propose an improved mutation operation with edge transformation. Experimental results show that our algorithm from a global perspective of multilayer structure can achieve the best solution quality among the existing algorithms. Finally, to our best knowledge, it is the first work to address both manhattan and non-manhattan routing at the same time. |
| Tasks | |
| Published | 2018-11-26 |
| URL | http://arxiv.org/abs/1811.10225v1 |
| http://arxiv.org/pdf/1811.10225v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-particle-swarm-optimizer-with-multi |
| Repo | |
| Framework | |
Biologically Motivated Algorithms for Propagating Local Target Representations
| Title | Biologically Motivated Algorithms for Propagating Local Target Representations |
| Authors | Alexander G. Ororbia, Ankur Mali |
| Abstract | Finding biologically plausible alternatives to back-propagation of errors is a fundamentally important challenge in artificial neural network research. In this paper, we propose a learning algorithm called error-driven Local Representation Alignment (LRA-E), which has strong connections to predictive coding, a theory that offers a mechanistic way of describing neurocomputational machinery. In addition, we propose an improved variant of Difference Target Propagation, another procedure that comes from the same family of algorithms as LRA-E. We compare our procedures to several other biologically-motivated algorithms, including two feedback alignment algorithms and Equilibrium Propagation. In two benchmarks, we find that both of our proposed algorithms yield stable performance and strong generalization compared to other competing back-propagation alternatives when training deeper, highly nonlinear networks, with LRA-E performing the best overall. |
| Tasks | |
| Published | 2018-05-26 |
| URL | http://arxiv.org/abs/1805.11703v3 |
| http://arxiv.org/pdf/1805.11703v3.pdf | |
| PWC | https://paperswithcode.com/paper/biologically-motivated-algorithms-for |
| Repo | |
| Framework | |
A context-based geoprocessing framework for optimizing meetup location of multiple moving objects along road networks
| Title | A context-based geoprocessing framework for optimizing meetup location of multiple moving objects along road networks |
| Authors | Shaohua Wang, Song Gao, Xin Feng, Alan T. Murray, Yuan Zeng |
| Abstract | Given different types of constraints on human life, people must make decisions that satisfy social activity needs. Minimizing costs (i.e., distance, time, or money) associated with travel plays an important role in perceived and realized social quality of life. Identifying optimal interaction locations on road networks when there are multiple moving objects (MMO) with space-time constraints remains a challenge. In this research, we formalize the problem of finding dynamic ideal interaction locations for MMO as a spatial optimization model and introduce a context-based geoprocessing heuristic framework to address this problem. As a proof of concept, a case study involving identification of a meetup location for multiple people under traffic conditions is used to validate the proposed geoprocessing framework. Five heuristic methods with regard to efficient shortest-path search space have been tested. We find that the R* tree-based algorithm performs the best with high quality solutions and low computation time. This framework is implemented in a GIS environment to facilitate integration with external geographic contextual information, e.g., temporary road barriers, points of interest (POI), and real-time traffic information, when dynamically searching for ideal meetup sites. The proposed method can be applied in trip planning, carpooling services, collaborative interaction, and logistics management. |
| Tasks | |
| Published | 2018-12-10 |
| URL | http://arxiv.org/abs/1812.03625v1 |
| http://arxiv.org/pdf/1812.03625v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-context-based-geoprocessing-framework-for |
| Repo | |
| Framework | |
Generating Synthetic X-ray Images of a Person from the Surface Geometry
| Title | Generating Synthetic X-ray Images of a Person from the Surface Geometry |
| Authors | Brian Teixeira, Vivek Singh, Terrence Chen, Kai Ma, Birgi Tamersoy, Yifan Wu, Elena Balashova, Dorin Comaniciu |
| Abstract | We present a novel framework that learns to predict human anatomy from body surface. Specifically, our approach generates a synthetic X-ray image of a person only from the person’s surface geometry. Furthermore, the synthetic X-ray image is parametrized and can be manipulated by adjusting a set of body markers which are also generated during the X-ray image prediction. With the proposed framework, multiple synthetic X-ray images can easily be generated by varying surface geometry. By perturbing the parameters, several additional synthetic X-ray images can be generated from the same surface geometry. As a result, our approach offers a potential to overcome the training data barrier in the medical domain. This capability is achieved by learning a pair of networks - one learns to generate the full image from the partial image and a set of parameters, and the other learns to estimate the parameters given the full image. During training, the two networks are trained iteratively such that they would converge to a solution where the predicted parameters and the full image are consistent with each other. In addition to medical data enrichment, our framework can also be used for image completion as well as anomaly detection. |
| Tasks | Anomaly Detection |
| Published | 2018-05-01 |
| URL | http://arxiv.org/abs/1805.00553v2 |
| http://arxiv.org/pdf/1805.00553v2.pdf | |
| PWC | https://paperswithcode.com/paper/generating-synthetic-x-ray-images-of-a-person |
| Repo | |
| Framework | |
