Paper Group ANR 1195
Super-Resolution of PROBA-V Images Using Convolutional Neural Networks. On the Reduction of Variance and Overestimation of Deep Q-Learning. Hybrid Machine Learning Approach to Popularity Prediction of Newly Released Contents for Online Video Streaming Service. Unsupervised Domain Adaptation using Generative Adversarial Networks for Semantic Segment …
Super-Resolution of PROBA-V Images Using Convolutional Neural Networks
| Title | Super-Resolution of PROBA-V Images Using Convolutional Neural Networks |
| Authors | Marcus Märtens, Dario Izzo, Andrej Krzic, Daniël Cox |
| Abstract | ESA’s PROBA-V Earth observation satellite enables us to monitor our planet at a large scale, studying the interaction between vegetation and climate and provides guidance for important decisions on our common global future. However, the interval at which high resolution images are recorded spans over several days, in contrast to the availability of lower resolution images which is often daily. We collect an extensive dataset of both, high and low resolution images taken by PROBA-V instruments during monthly periods to investigate Multi Image Super-resolution, a technique to merge several low resolution images to one image of higher quality. We propose a convolutional neural network that is able to cope with changes in illumination, cloud coverage and landscape features which are challenges introduced by the fact that the different images are taken over successive satellite passages over the same region. Given a bicubic upscaling of low resolution images taken under optimal conditions, we find the Peak Signal to Noise Ratio of the reconstructed image of the network to be higher for a large majority of different scenes. This shows that applied machine learning has the potential to enhance large amounts of previously collected earth observation data during multiple satellite passes. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.01821v1 |
| https://arxiv.org/pdf/1907.01821v1.pdf | |
| PWC | https://paperswithcode.com/paper/super-resolution-of-proba-v-images-using |
| Repo | |
| Framework | |
On the Reduction of Variance and Overestimation of Deep Q-Learning
| Title | On the Reduction of Variance and Overestimation of Deep Q-Learning |
| Authors | Mohammed Sabry, Amr M. A. Khalifa |
| Abstract | The breakthrough of deep Q-Learning on different types of environments revolutionized the algorithmic design of Reinforcement Learning to introduce more stable and robust algorithms, to that end many extensions to deep Q-Learning algorithm have been proposed to reduce the variance of the target values and the overestimation phenomena. In this paper, we examine new methodology to solve these issues, we propose using Dropout techniques on deep Q-Learning algorithm as a way to reduce variance and overestimation. We further present experiments on some of the benchmark environments that demonstrate significant improvement of the stability of the performance and a reduction in variance and overestimation. |
| Tasks | Q-Learning |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.05983v1 |
| https://arxiv.org/pdf/1910.05983v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-reduction-of-variance-and |
| Repo | |
| Framework | |
Hybrid Machine Learning Approach to Popularity Prediction of Newly Released Contents for Online Video Streaming Service
| Title | Hybrid Machine Learning Approach to Popularity Prediction of Newly Released Contents for Online Video Streaming Service |
| Authors | Hongjun Jeon, Wonchul Seo, Eunjeong Lucy Park, Sungchul Choi |
| Abstract | In the industry of video content providers such as VOD and IPTV, predicting the popularity of video contents in advance is critical not only from a marketing perspective but also from a network optimization perspective. By predicting whether the content will be successful or not in advance, the content file, which is large, is efficiently deployed in the proper service providing server, leading to network cost optimization. Many previous studies have done view count prediction research to do this. However, the studies have been making predictions based on historical view count data from users. In this case, the contents had been published to the users and already deployed on a service server. These approaches make possible to efficiently deploy a content already published but are impossible to use for a content that is not be published. To address the problems, this research proposes a hybrid machine learning approach to the classification model for the popularity prediction of newly video contents which is not published. In this paper, we create a new variable based on the related content of the specific content and divide entire dataset by the characteristics of the contents. Next, the prediction is performed using XGBoosting and deep neural net based model according to the data characteristics of the cluster. Our model uses metadata for contents for prediction, so we use categorical embedding techniques to solve the sparsity of categorical variables and make them learn efficiently for the deep neural net model. As well, we use the FTRL-proximal algorithm to solve the problem of the view-count volatility of video content. We achieve overall better performance than the previous standalone method with a dataset from one of the top streaming service company. |
| Tasks | |
| Published | 2019-01-28 |
| URL | http://arxiv.org/abs/1901.09613v1 |
| http://arxiv.org/pdf/1901.09613v1.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-machine-learning-approach-to |
| Repo | |
| Framework | |
Unsupervised Domain Adaptation using Generative Adversarial Networks for Semantic Segmentation of Aerial Images
| Title | Unsupervised Domain Adaptation using Generative Adversarial Networks for Semantic Segmentation of Aerial Images |
| Authors | Bilel Benjdira, Yakoub Bazi, Anis Koubaa, Kais Ouni |
| Abstract | Segmenting aerial images is being of great potential in surveillance and scene understanding of urban areas. It provides a mean for automatic reporting of the different events that happen in inhabited areas. This remarkably promotes public safety and traffic management applications. After the wide adoption of convolutional neural networks methods, the accuracy of semantic segmentation algorithms could easily surpass 80% if a robust dataset is provided. Despite this success, the deployment of a pre-trained segmentation model to survey a new city that is not included in the training set significantly decreases the accuracy. This is due to the domain shift between the source dataset on which the model is trained and the new target domain of the new city images. In this paper, we address this issue and consider the challenge of domain adaptation in semantic segmentation of aerial images. We design an algorithm that reduces the domain shift impact using Generative Adversarial Networks (GANs). In the experiments, we test the proposed methodology on the International Society for Photogrammetry and Remote Sensing (ISPRS) semantic segmentation dataset and found that our method improves the overall accuracy from 35% to 52% when passing from Potsdam domain (considered as source domain) to Vaihingen domain (considered as target domain). In addition, the method allows recovering efficiently the inverted classes due to sensor variation. In particular, it improves the average segmentation accuracy of the inverted classes due to sensor variation from 14% to 61%. |
| Tasks | Domain Adaptation, Scene Understanding, Semantic Segmentation, Unsupervised Domain Adaptation |
| Published | 2019-05-08 |
| URL | https://arxiv.org/abs/1905.03198v1 |
| https://arxiv.org/pdf/1905.03198v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-using-3 |
| Repo | |
| Framework | |
Anatomical Priors for Image Segmentation via Post-Processing with Denoising Autoencoders
| Title | Anatomical Priors for Image Segmentation via Post-Processing with Denoising Autoencoders |
| Authors | Agostina J. Larrazabal, Cesar Martinez, Enzo Ferrante |
| Abstract | Deep convolutional neural networks (CNN) proved to be highly accurate to perform anatomical segmentation of medical images. However, some of the most popular CNN architectures for image segmentation still rely on post-processing strategies (e.g. Conditional Random Fields) to incorporate connectivity constraints into the resulting masks. These post-processing steps are based on the assumption that objects are usually continuous and therefore nearby pixels should be assigned the same object label. Even if it is a valid assumption in general, these methods do not offer a straightforward way to incorporate more complex priors like convexity or arbitrary shape restrictions. In this work we propose Post-DAE, a post-processing method based on denoising autoencoders (DAE) trained using only segmentation masks. We learn a low-dimensional space of anatomically plausible segmentations, and use it as a post-processing step to impose shape constraints on the resulting masks obtained with arbitrary segmentation methods. Our approach is independent of image modality and intensity information since it employs only segmentation masks for training. This enables the use of anatomical segmentations that do not need to be paired with intensity images, making the approach very flexible. Our experimental results on anatomical segmentation of X-ray images show that Post-DAE can improve the quality of noisy and incorrect segmentation masks obtained with a variety of standard methods, by bringing them back to a feasible space, with almost no extra computational time. |
| Tasks | Denoising, Semantic Segmentation |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02343v1 |
| https://arxiv.org/pdf/1906.02343v1.pdf | |
| PWC | https://paperswithcode.com/paper/190602343 |
| Repo | |
| Framework | |
The Open Vault Challenge – Learning how to build calibration-free interactive systems by cracking the code of a vault
| Title | The Open Vault Challenge – Learning how to build calibration-free interactive systems by cracking the code of a vault |
| Authors | Jonathan Grizou |
| Abstract | This demo takes the form of a challenge to the IJCAI community. A physical vault, secured by a 4-digit code, will be placed in the demo area. The author will publicly open the vault by entering the code on a touch-based interface, and as many times as requested. The challenge to the IJCAI participants will be to crack the code, open the vault, and collect its content. The interface is based on previous work on calibration-free interactive systems that enables a user to start instructing a machine without the machine knowing how to interpret the user’s actions beforehand. The intent and the behavior of the human are simultaneously learned by the machine. An online demo and videos are available for readers to participate in the challenge. An additional interface using vocal commands will be revealed on the demo day, demonstrating the scalability of our approach to continuous input signals. |
| Tasks | Calibration |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02485v1 |
| https://arxiv.org/pdf/1906.02485v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-open-vault-challenge-learning-how-to |
| Repo | |
| Framework | |
Sliding window property testing for regular languages
| Title | Sliding window property testing for regular languages |
| Authors | Moses Ganardi, Danny Hucke, Markus Lohrey, Tatiana Starikovskaya |
| Abstract | We study the problem of recognizing regular languages in a variant of the streaming model of computation, called the sliding window model. In this model, we are given a size of the sliding window $n$ and a stream of symbols. At each time instant, we must decide whether the suffix of length $n$ of the current stream (“the active window”) belongs to a given regular language. Recent works showed that the space complexity of an optimal deterministic sliding window algorithm for this problem is either constant, logarithmic or linear in the window size $n$ and provided natural language theoretic characterizations of the space complexity classes. Subsequently, those results were extended to randomized algorithms to show that any such algorithm admits either constant, double logarithmic, logarithmic or linear space complexity. In this work, we make an important step forward and combine the sliding window model with the property testing setting, which results in ultra-efficient algorithms for all regular languages. Informally, a sliding window property tester must accept the active window if it belongs to the language and reject it if it is far from the language. We consider deterministic and randomized sliding window property testers with one-sided and two-sided errors. In particular, we show that for any regular language, there is a deterministic sliding window property tester that uses logarithmic space and a randomized sliding window property tester with two-sided error that uses constant space. |
| Tasks | |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10261v1 |
| https://arxiv.org/pdf/1909.10261v1.pdf | |
| PWC | https://paperswithcode.com/paper/190910261 |
| Repo | |
| Framework | |
FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization
| Title | FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization |
| Authors | Amirhossein Reisizadeh, Aryan Mokhtari, Hamed Hassani, Ali Jadbabaie, Ramtin Pedarsani |
| Abstract | Federated learning is a distributed framework according to which a model is trained over a set of devices, while keeping data localized. This framework faces several systems-oriented challenges which include (i) communication bottleneck since a large number of devices upload their local updates to a parameter server, and (ii) scalability as the federated network consists of millions of devices. Due to these systems challenges as well as issues related to statistical heterogeneity of data and privacy concerns, designing a provably efficient federated learning method is of significant importance yet it remains challenging. In this paper, we present FedPAQ, a communication-efficient Federated Learning method with Periodic Averaging and Quantization. FedPAQ relies on three key features: (1) periodic averaging where models are updated locally at devices and only periodically averaged at the server; (2) partial device participation where only a fraction of devices participate in each round of the training; and (3) quantized message-passing where the edge nodes quantize their updates before uploading to the parameter server. These features address the communications and scalability challenges in federated learning. We also show that FedPAQ achieves near-optimal theoretical guarantees for strongly convex and non-convex loss functions and empirically demonstrate the communication-computation tradeoff provided by our method. |
| Tasks | Quantization |
| Published | 2019-09-28 |
| URL | https://arxiv.org/abs/1909.13014v3 |
| https://arxiv.org/pdf/1909.13014v3.pdf | |
| PWC | https://paperswithcode.com/paper/fedpaq-a-communication-efficient-federated |
| Repo | |
| Framework | |
Bayesian Differential Privacy for Machine Learning
| Title | Bayesian Differential Privacy for Machine Learning |
| Authors | Aleksei Triastcyn, Boi Faltings |
| Abstract | We propose Bayesian differential privacy, a relaxation of differential privacy that provides more practical privacy guarantees for similarly distributed data, especially in difficult scenarios, such as deep learning. We derive a general privacy accounting method for iterative learning algorithms under Bayesian differential privacy and show that it is a generalisation of the well-known moments accountant. Our experiments demonstrate significant improvements in privacy guarantees for typical deep learning datasets, such as MNIST and CIFAR-10, in some cases bringing the privacy budget from 8 down to 0.5. Additionally, we demonstrate applicability of Bayesian differential privacy to variational inference and achieve the state-of-the-art privacy-accuracy trade-off. |
| Tasks | |
| Published | 2019-01-28 |
| URL | https://arxiv.org/abs/1901.09697v4 |
| https://arxiv.org/pdf/1901.09697v4.pdf | |
| PWC | https://paperswithcode.com/paper/improved-accounting-for-differentially |
| Repo | |
| Framework | |
Automatic Calibration of Dynamic and Heterogeneous Parameters in Agent-based Model
| Title | Automatic Calibration of Dynamic and Heterogeneous Parameters in Agent-based Model |
| Authors | Dongjun Kim, Tae-Sub Yun, Il-Chul Moon |
| Abstract | While simulations have been utilized in diverse domains, such as urban growth modeling, market dynamics modeling, etc; some of these applications may require validations based upon some real-world observations modeled in the simulation, as well. This validation has been categorized into either qualitative face-validation or quantitative empirical validation, but as the importance and the accumulation of data grows, the importance of the quantitative validation has been highlighted in the recent studies, i.e. digital twin. The key component of quantitative validation is finding a calibrated set of parameters to regenerate the real-world observations with simulation models. While this parameter calibration has been fixed throughout a simulation execution, this paper expands the static parameter calibration in two dimensions: dynamic calibration and heterogeneous calibration. First, dynamic calibration changes the parameter values over the simulation period by reflecting the simulation output trend. Second, heterogeneous calibration changes the parameter values per simulated entity clusters by considering the similarities of entity states. We experimented the suggested calibrations on one hypothetical case and another real-world case. As a hypothetical scenario, we use the Wealth Distribution Model to illustrate how our calibration works. As a real-world scenario, we selected Real Estate Market Model because of three reasons. First, the models have heterogeneous entities as being agent-based models; second, they are economic models with real-world trends over time; and third, they are applicable to the real-world scenarios where we can gather validation data. |
| Tasks | Calibration |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03309v1 |
| https://arxiv.org/pdf/1908.03309v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-calibration-of-dynamic-and |
| Repo | |
| Framework | |
A Novel Self-Supervised Re-labeling Approach for Training with Noisy Labels
| Title | A Novel Self-Supervised Re-labeling Approach for Training with Noisy Labels |
| Authors | Devraj Mandal, Shrisha Bharadwaj, Soma Biswas |
| Abstract | The major driving force behind the immense success of deep learning models is the availability of large datasets along with their clean labels. Unfortunately, this is very difficult to obtain, which has motivated research on the training of deep models in the presence of label noise and ways to avoid over-fitting on the noisy labels. In this work, we build upon the seminal work in this area, Co-teaching and propose a simple, yet efficient approach termed mCT-S2R (modified co-teaching with self-supervision and re-labeling) for this task. First, to deal with significant amount of noise in the labels, we propose to use self-supervision to generate robust features without using any labels. Next, using a parallel network architecture, an estimate of the clean labeled portion of the data is obtained. Finally, using this data, a portion of the estimated noisy labeled portion is re-labeled, before resuming the network training with the augmented data. Extensive experiments on three standard datasets show the effectiveness of the proposed framework. |
| Tasks | |
| Published | 2019-10-13 |
| URL | https://arxiv.org/abs/1910.05700v3 |
| https://arxiv.org/pdf/1910.05700v3.pdf | |
| PWC | https://paperswithcode.com/paper/what-happens-when-self-supervision-meets |
| Repo | |
| Framework | |
On the Mathematical Understanding of ResNet with Feynman Path Integral
| Title | On the Mathematical Understanding of ResNet with Feynman Path Integral |
| Authors | Minghao Yin, Xiu Li, Yongbing Zhang, Shiqi Wang |
| Abstract | In this paper, we aim to understand Residual Network (ResNet) in a scientifically sound way by providing a bridge between ResNet and Feynman path integral. In particular, we prove that the effect of residual block is equivalent to partial differential equation, and the ResNet transforming process can be equivalently converted to Feynman path integral. These conclusions greatly help us mathematically understand the advantage of ResNet in addressing the gradient vanishing issue. More importantly, our analyses offer a path integral view of ResNet, and demonstrate that the output of certain network can be obtained by adding contributions of all paths. Moreover, the contribution of each path is proportional to e^{-S}, where S is the action given by time integral of Lagrangian L. This lays the solid foundation in the understanding of ResNet, and provides insights in the future design of convolutional neural network architecture. Based on these results, we have designed the network using partial differential operators, which further validates our theoritical analyses. |
| Tasks | |
| Published | 2019-04-16 |
| URL | http://arxiv.org/abs/1904.07568v1 |
| http://arxiv.org/pdf/1904.07568v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-mathematical-understanding-of-resnet |
| Repo | |
| Framework | |
Towards Machine-assisted Meta-Studies: The Hubble Constant
| Title | Towards Machine-assisted Meta-Studies: The Hubble Constant |
| Authors | Tom Crossland, Pontus Stenetorp, Sebastian Riedel, Daisuke Kawata, Thomas D. Kitching, Rupert A. C. Croft |
| Abstract | We present an approach for automatic extraction of measured values from the astrophysical literature, using the Hubble constant for our pilot study. Our rules-based model – a classical technique in natural language processing – has successfully extracted 298 measurements of the Hubble constant, with uncertainties, from the 208,541 available arXiv astrophysics papers. We have also created an artificial neural network classifier to identify papers in arXiv which report novel measurements. From the analysis of our results we find that reporting measurements with uncertainties and the correct units is critical information when distinguishing novel measurements in free text. Our results correctly highlight the current tension for measurements of the Hubble constant and recover the $3.5\sigma$ discrepancy – demonstrating that the tool presented in this paper is useful for meta-studies of astrophysical measurements from a large number of publications. |
| Tasks | |
| Published | 2019-01-31 |
| URL | https://arxiv.org/abs/1902.00027v2 |
| https://arxiv.org/pdf/1902.00027v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-machine-assisted-meta-studies-the |
| Repo | |
| Framework | |
Attack on Grid Event Cause Analysis: An Adversarial Machine Learning Approach
| Title | Attack on Grid Event Cause Analysis: An Adversarial Machine Learning Approach |
| Authors | Iman Niazazari, Hanif Livani |
| Abstract | With the ever-increasing reliance on data for data-driven applications in power grids, such as event cause analysis, the authenticity of data streams has become crucially important. The data can be prone to adversarial stealthy attacks aiming to manipulate the data such that residual-based bad data detectors cannot detect them, and the perception of system operators or event classifiers changes about the actual event. This paper investigates the impact of adversarial attacks on convolutional neural network-based event cause analysis frameworks. We have successfully verified the ability of adversaries to maliciously misclassify events through stealthy data manipulations. The vulnerability assessment is studied with respect to the number of compromised measurements. Furthermore, a defense mechanism to robustify the performance of the event cause analysis is proposed. The effectiveness of adversarial attacks on changing the output of the framework is studied using the data generated by real-time digital simulator (RTDS) under different scenarios such as type of attacks and level of access to data. |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08011v2 |
| https://arxiv.org/pdf/1911.08011v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-attacks-on-grid-events |
| Repo | |
| Framework | |
Model-Free Unsupervised Learning for Optimization Problems with Constraints
| Title | Model-Free Unsupervised Learning for Optimization Problems with Constraints |
| Authors | Chengjian Sun, Dong Liu, Chenyang Yang |
| Abstract | In many optimization problems in wireless communications, the expressions of objective function or constraints are hard or even impossible to derive, which makes the solutions difficult to find. In this paper, we propose a model-free learning framework to solve constrained optimization problems without the supervision of the optimal solution. Neural networks are used respectively for parameterizing the function to be optimized, parameterizing the Lagrange multiplier associated with instantaneous constraints, and approximating the unknown objective function or constraints. We provide learning algorithms to train all the neural networks simultaneously, and reveal the connections of the proposed framework with reinforcement learning. Numerical and simulation results validate the proposed framework and demonstrate the efficiency of model-free learning by taking power control problem as an example. |
| Tasks | |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.12706v1 |
| https://arxiv.org/pdf/1907.12706v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-free-unsupervised-learning-for |
| Repo | |
| Framework | |
