Paper Group ANR 1191
What Can Machine Learning Teach Us about Communications?. LMF Reloaded. Building Segmentation through a Gated Graph Convolutional Neural Network with Deep Structured Feature Embedding. DeepTagRec: A Content-cum-User based Tag Recommendation Framework for Stack Overflow. Epoch-wise label attacks for robustness against label noise. Statistical Infere …
What Can Machine Learning Teach Us about Communications?
| Title | What Can Machine Learning Teach Us about Communications? |
| Authors | Mengke Lian, Christian Häger, Henry D. Pfister |
| Abstract | Rapid improvements in machine learning over the past decade are beginning to have far-reaching effects. For communications, engineers with limited domain expertise can now use off-the-shelf learning packages to design high-performance systems based on simulations. Prior to the current revolution in machine learning, the majority of communication engineers were quite aware that system parameters (such as filter coefficients) could be learned using stochastic gradient descent. It was not at all clear, however, that more complicated parts of the system architecture could be learned as well. In this paper, we discuss the application of machine-learning techniques to two communications problems and focus on what can be learned from the resulting systems. We were pleasantly surprised that the observed gains in one example have a simple explanation that only became clear in hindsight. In essence, deep learning discovered a simple and effective strategy that had not been considered earlier. |
| Tasks | |
| Published | 2019-01-22 |
| URL | http://arxiv.org/abs/1901.07592v2 |
| http://arxiv.org/pdf/1901.07592v2.pdf | |
| PWC | https://paperswithcode.com/paper/what-can-machine-learning-teach-us-about |
| Repo | |
| Framework | |
LMF Reloaded
| Title | LMF Reloaded |
| Authors | Laurent Romary, Mohamed Khemakhem, Fahad Khan, Jack Bowers, Nicoletta Calzolari, Monte George, Mandy Pet, Piotr Bański |
| Abstract | Lexical Markup Framework (LMF) or ISO 24613 [1] is a de jure standard that provides a framework for modelling and encoding lexical information in retrodigitised print dictionaries and NLP lexical databases. An in-depth review is currently underway within the standardisation subcommittee , ISO-TC37/SC4/WG4, to find a more modular, flexible and durable follow up to the original LMF standard published in 2008. In this paper we will present some of the major improvements which have so far been implemented in the new version of LMF. |
| Tasks | |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1906.02136v1 |
| https://arxiv.org/pdf/1906.02136v1.pdf | |
| PWC | https://paperswithcode.com/paper/190602136 |
| Repo | |
| Framework | |
Building Segmentation through a Gated Graph Convolutional Neural Network with Deep Structured Feature Embedding
| Title | Building Segmentation through a Gated Graph Convolutional Neural Network with Deep Structured Feature Embedding |
| Authors | Yilei Shi, Qingyu Li, Xiao Xiang Zhu |
| Abstract | Automatic building extraction from optical imagery remains a challenge due to, for example, the complexity of building shapes. Semantic segmentation is an efficient approach for this task. The latest development in deep convolutional neural networks (DCNNs) has made accurate pixel-level classification tasks possible. Yet one central issue remains: the precise delineation of boundaries. Deep architectures generally fail to produce fine-grained segmentation with accurate boundaries due to their progressive down-sampling. Hence, we introduce a generic framework to overcome the issue, integrating the graph convolutional network (GCN) and deep structured feature embedding (DSFE) into an end-to-end workflow. Furthermore, instead of using a classic graph convolutional neural network, we propose a gated graph convolutional network, which enables the refinement of weak and coarse semantic predictions to generate sharp borders and fine-grained pixel-level classification. Taking the semantic segmentation of building footprints as a practical example, we compared different feature embedding architectures and graph neural networks. Our proposed framework with the new GCN architecture outperforms state-of-the-art approaches. Although our main task in this work is building footprint extraction, the proposed method can be generally applied to other binary or multi-label segmentation tasks. |
| Tasks | Semantic Segmentation |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03165v1 |
| https://arxiv.org/pdf/1911.03165v1.pdf | |
| PWC | https://paperswithcode.com/paper/building-segmentation-through-a-gated-graph |
| Repo | |
| Framework | |
DeepTagRec: A Content-cum-User based Tag Recommendation Framework for Stack Overflow
| Title | DeepTagRec: A Content-cum-User based Tag Recommendation Framework for Stack Overflow |
| Authors | Suman Kalyan Maity, Abhishek Panigrahi, Sayan Ghosh, Arundhati Banerjee, Pawan Goyal, Animesh Mukherjee |
| Abstract | In this paper, we develop a content-cum-user based deep learning framework DeepTagRec to recommend appropriate question tags on Stack Overflow. The proposed system learns the content representation from question title and body. Subsequently, the learnt representation from heterogeneous relationship between user and tags is fused with the content representation for the final tag prediction. On a very large-scale dataset comprising half a million question posts, DeepTagRec beats all the baselines; in particular, it significantly outperforms the best performing baseline T agCombine achieving an overall gain of 60.8% and 36.8% in precision@3 and recall@10 respectively. DeepTagRec also achieves 63% and 33.14% maximum improvement in exact-k accuracy and top-k accuracy respectively over TagCombine |
| Tasks | |
| Published | 2019-03-10 |
| URL | http://arxiv.org/abs/1903.03941v1 |
| http://arxiv.org/pdf/1903.03941v1.pdf | |
| PWC | https://paperswithcode.com/paper/deeptagrec-a-content-cum-user-based-tag |
| Repo | |
| Framework | |
Epoch-wise label attacks for robustness against label noise
| Title | Epoch-wise label attacks for robustness against label noise |
| Authors | Sebastian Guendel, Andreas Maier |
| Abstract | The current accessibility to large medical datasets for training convolutional neural networks is tremendously high. The associated dataset labels are always considered to be the real “ground truth”. However, the labeling procedures often seem to be inaccurate and many wrong labels are integrated. This may have fatal consequences on the performance of both training and evaluation. In this paper, we show the impact of label noise in the training set on a specific medical problem based on chest X-ray images. With a simple one-class problem, the classification of tuberculosis, we measure the performance on a clean evaluation set when training with label-corrupt data. We develop a method to compete with incorrectly labeled data during training by randomly attacking labels on individual epochs. The network tends to be robust when flipping correct labels for a single epoch and initiates a good step to the optimal minimum on the error surface when flipping noisy labels. On a baseline with an AUC (Area under Curve) score of 0.924, the performance drops to 0.809 when 30% of our training data is misclassified. With our approach the baseline performance could almost be maintained, the performance raised to 0.918. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.01966v2 |
| https://arxiv.org/pdf/1912.01966v2.pdf | |
| PWC | https://paperswithcode.com/paper/epoch-wise-label-attacks-for-robustness |
| Repo | |
| Framework | |
Statistical Inference for Generative Models with Maximum Mean Discrepancy
| Title | Statistical Inference for Generative Models with Maximum Mean Discrepancy |
| Authors | Francois-Xavier Briol, Alessandro Barp, Andrew B. Duncan, Mark Girolami |
| Abstract | While likelihood-based inference and its variants provide a statistically efficient and widely applicable approach to parametric inference, their application to models involving intractable likelihoods poses challenges. In this work, we study a class of minimum distance estimators for intractable generative models, that is, statistical models for which the likelihood is intractable, but simulation is cheap. The distance considered, maximum mean discrepancy (MMD), is defined through the embedding of probability measures into a reproducing kernel Hilbert space. We study the theoretical properties of these estimators, showing that they are consistent, asymptotically normal and robust to model misspecification. A main advantage of these estimators is the flexibility offered by the choice of kernel, which can be used to trade-off statistical efficiency and robustness. On the algorithmic side, we study the geometry induced by MMD on the parameter space and use this to introduce a novel natural gradient descent-like algorithm for efficient implementation of these estimators. We illustrate the relevance of our theoretical results on several classes of models including a discrete-time latent Markov process and two multivariate stochastic differential equation models. |
| Tasks | |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05944v1 |
| https://arxiv.org/pdf/1906.05944v1.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-inference-for-generative-models |
| Repo | |
| Framework | |
Pure and Spurious Critical Points: a Geometric Study of Linear Networks
| Title | Pure and Spurious Critical Points: a Geometric Study of Linear Networks |
| Authors | Matthew Trager, Kathlén Kohn, Joan Bruna |
| Abstract | The critical locus of the loss function of a neural network is determined by the geometry of the functional space and by the parameterization of this space by the network’s weights. We introduce a natural distinction between pure critical points, which only depend on the functional space, and spurious critical points, which arise from the parameterization. We apply this perspective to revisit and extend the literature on the loss function of linear neural networks. For this type of network, the functional space is either the set of all linear maps from input to output space, or a determinantal variety, i.e., a set of linear maps with bounded rank. We use geometric properties of determinantal varieties to derive new results on the landscape of linear networks with different loss functions and different parameterizations. |
| Tasks | |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01671v1 |
| https://arxiv.org/pdf/1910.01671v1.pdf | |
| PWC | https://paperswithcode.com/paper/pure-and-spurious-critical-points-a-geometric |
| Repo | |
| Framework | |
Addict Free – A Smart and Connected Relapse Intervention Mobile App
| Title | Addict Free – A Smart and Connected Relapse Intervention Mobile App |
| Authors | Zhou Yang, Vinay Jayachandra Reddy, Rashmi Kesidi, Fang Jin |
| Abstract | It is widely acknowledged that addiction relapse is highly associated with spatial-temporal factors such as some specific places or time periods. Current studies suggest that those factors can be utilized for better relapse interventions, however, there is no relapse prevention application that makes use of those factors. In this paper, we introduce a mobile app called “Addict Free”, which records user profiles, tracks relapse history and summarizes recovering statistics to help users better understand their recovering situations. Also, this app builds a relapse recovering community, which allows users to ask for advice and encouragement, and share relapse prevention experience. Moreover, machine learning algorithms that ingest spatial and temporal factors are utilized to predict relapse, based on which helpful addiction diversion activities are recommended by a recovering recommendation algorithm. By interacting with users, this app targets at providing smart suggestions that aim to stop relapse, especially for alcohol and tobacco addiction users. |
| Tasks | |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.01130v1 |
| https://arxiv.org/pdf/1912.01130v1.pdf | |
| PWC | https://paperswithcode.com/paper/addict-free-a-smart-and-connected-relapse |
| Repo | |
| Framework | |
Exploring the Intersections of Web Science and Accessibility
| Title | Exploring the Intersections of Web Science and Accessibility |
| Authors | Trevor Bostic, Jeff Stanley, John Higgins, Rachael L. Bradley-Montgomery, Justin F. Brunelle, Daniel Chudnov |
| Abstract | The web is the prominent way information is exchanged in the 21st century. However, ensuring web-based information is accessible is complicated, particularly with web applications that rely on JavaScript and other technologies to deliver and build representations; representations are often the HTML, images, or other code a server delivers for a web resource. Static representations are becoming rarer and assessing the accessibility of web-based information to ensure it is available to all users is increasingly difficult given the dynamic nature of representations. In this work, we survey three ongoing research threads that can inform web accessibility solutions: assessing web accessibility, modeling web user activity, and web application crawling. Current web accessibility research is continually focused on increasing the percentage of automatically testable standards, but still relies heavily upon manual testing for complex interactive applications. Along-side web accessibility research, there are mechanisms developed by researchers that replicate user interactions with web pages based on usage patterns. Crawling web applications is a broad research domain; exposing content in web applications is difficult because of incompatibilities in web crawlers and the technologies used to create the applications. We describe research on crawling the deep web by exercising user forms. We close with a thought exercise regarding the convergence of these three threads and the future of automated, web-based accessibility evaluation and assurance through a use case in web archiving. These research efforts provide insight into how users interact with websites, how to automate and simulate user interactions, how to record the results of user interactions, and how to analyze, evaluate, and map resulting website content to determine its relative accessibility. |
| Tasks | |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.02804v1 |
| https://arxiv.org/pdf/1908.02804v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-the-intersections-of-web-science |
| Repo | |
| Framework | |
MetalGAN: a Cluster-based Adaptive Training for Few-Shot Adversarial Colorization
| Title | MetalGAN: a Cluster-based Adaptive Training for Few-Shot Adversarial Colorization |
| Authors | Tomaso Fontanini, Eleonora Iotti, Andrea Prati |
| Abstract | In recent years, the majority of works on deep-learning-based image colorization have focused on how to make a good use of the enormous datasets currently available. What about when the data at disposal are scarce? The main objective of this work is to prove that a network can be trained and can provide excellent colorization results even without a large quantity of data. The adopted approach is a mixed one, which uses an adversarial method for the actual colorization, and a meta-learning technique to enhance the generator model. Also, a clusterization a-priori of the training dataset ensures a task-oriented division useful for meta-learning, and at the same time reduces the per-step number of images. This paper describes in detail the method and its main motivations, and a discussion of results and future developments is provided. |
| Tasks | Colorization, Meta-Learning |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07654v1 |
| https://arxiv.org/pdf/1909.07654v1.pdf | |
| PWC | https://paperswithcode.com/paper/metalgan-a-cluster-based-adaptive-training |
| Repo | |
| Framework | |
Real-time Intent Prediction of Pedestrians for Autonomous Ground Vehicles via Spatio-Temporal DenseNet
| Title | Real-time Intent Prediction of Pedestrians for Autonomous Ground Vehicles via Spatio-Temporal DenseNet |
| Authors | Khaled Saleh, Mohammed Hossny, Saeid Nahavandi |
| Abstract | Understanding the behaviors and intentions of humans are one of the main challenges autonomous ground vehicles still faced with. More specifically, when it comes to complex environments such as urban traffic scenes, inferring the intentions and actions of vulnerable road users such as pedestrians become even harder. In this paper, we address the problem of intent action prediction of pedestrians in urban traffic environments using only image sequences from a monocular RGB camera. We propose a real-time framework that can accurately detect, track and predict the intended actions of pedestrians based on a tracking-by-detection technique in conjunction with a novel spatio-temporal DenseNet model. We trained and evaluated our framework based on real data collected from urban traffic environments. Our framework has shown resilient and competitive results in comparison to other baseline approaches. Overall, we achieved an average precision score of 84.76% with a real-time performance at 20 FPS. |
| Tasks | |
| Published | 2019-04-22 |
| URL | http://arxiv.org/abs/1904.09862v1 |
| http://arxiv.org/pdf/1904.09862v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-intent-prediction-of-pedestrians |
| Repo | |
| Framework | |
Gaussian Process Priors for View-Aware Inference
| Title | Gaussian Process Priors for View-Aware Inference |
| Authors | Yuxin Hou, Ari Heljakka, Arno Solin |
| Abstract | We derive a principled framework for encoding prior knowledge of information coupling between views or camera poses (translation and orientation) of a single scene. While deep neural networks have become the prominent solution to many tasks in computer vision, some important problems not so well suited for deep models have received less attention. These include uncertainty quantification, auxiliary data fusion, and real-time processing, which are instrumental for delivering practical methods with robust inference. While these are central goals in probabilistic machine learning, there is a tangible gap between the theory and practice of applying probabilistic methods to many modern vision problems. For this, we derive a novel parametric kernel (covariance function) in the pose space, $\mathrm{SE}(3)$, that encodes information about input pose relationships into larger models. We show how this soft-prior knowledge can be applied to improve performance on several real vision tasks, such as feature tracking, human face encoding, and view synthesis. |
| Tasks | |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03249v1 |
| https://arxiv.org/pdf/1912.03249v1.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-process-priors-for-view-aware |
| Repo | |
| Framework | |
Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
| Title | Revisiting Shadow Detection: A New Benchmark Dataset for Complex World |
| Authors | Xiaowei Hu, Tianyu Wang, Chi-Wing Fu, Yitong Jiang, Qiong Wang, Pheng-Ann Heng |
| Abstract | Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types. Further, we comprehensively analyze the complexity of the dataset, present a fast shadow detection network with a detail enhancement module to harvest shadow details, and demonstrate the effectiveness of our method to detect shadows in general situations. |
| Tasks | Shadow Detection |
| Published | 2019-11-16 |
| URL | https://arxiv.org/abs/1911.06998v1 |
| https://arxiv.org/pdf/1911.06998v1.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-shadow-detection-a-new-benchmark |
| Repo | |
| Framework | |
A Paraconsistent ASP-like Language with Tractable Model Generation
| Title | A Paraconsistent ASP-like Language with Tractable Model Generation |
| Authors | Andrzej Szalas |
| Abstract | Answer Set Programming (ASP) is nowadays a dominant rule-based knowledge representation tool. Though existing ASP variants enjoy efficient implementations, generating an answer set remains intractable. The goal of this research is to define a new \asp-like rule language, 4SP, with tractable model generation. The language combines ideas of ASP and a paraconsistent rule language 4QL. Though 4SP shares the syntax of \asp and for each program all its answer sets are among 4SP models, the new language differs from ASP in its logical foundations, the intended methodology of its use and complexity of computing models. As we show in the paper, 4QL can be seen as a paraconsistent counterpart of ASP programs stratified with respect to default negation. Although model generation of well-supported models for 4QL programs is tractable, dropping stratification makes both 4QL and ASP intractable. To retain tractability while allowing non-stratified programs, in 4SP we introduce trial expressions interlacing programs with hypotheses as to the truth values of default negations. This allows us to develop a~model generation algorithm with deterministic polynomial time complexity. We also show relationships among 4SP, ASP and 4QL. |
| Tasks | |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09715v1 |
| https://arxiv.org/pdf/1912.09715v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-paraconsistent-asp-like-language-with |
| Repo | |
| Framework | |
Fully Automatic Video Colorization with Self-Regularization and Diversity
| Title | Fully Automatic Video Colorization with Self-Regularization and Diversity |
| Authors | Chenyang Lei, Qifeng Chen |
| Abstract | We present a fully automatic approach to video colorization with self-regularization and diversity. Our model contains a colorization network for video frame colorization and a refinement network for spatiotemporal color refinement. Without any labeled data, both networks can be trained with self-regularized losses defined in bilateral and temporal space. The bilateral loss enforces color consistency between neighboring pixels in a bilateral space and the temporal loss imposes constraints between corresponding pixels in two nearby frames. While video colorization is a multi-modal problem, our method uses a perceptual loss with diversity to differentiate various modes in the solution space. Perceptual experiments demonstrate that our approach outperforms state-of-the-art approaches on fully automatic video colorization. The results are shown in the supplementary video at https://youtu.be/Y15uv2jnK-4 |
| Tasks | Colorization |
| Published | 2019-08-04 |
| URL | https://arxiv.org/abs/1908.01311v1 |
| https://arxiv.org/pdf/1908.01311v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-automatic-video-colorization-with-self-1 |
| Repo | |
| Framework | |
