Paper Group ANR 368
Probabilistic Generative Adversarial Networks. On the EM-Tau algorithm: a new EM-style algorithm with partial E-steps. A Frequency Domain Neural Network for Fast Image Super-resolution. CREST: Convolutional Residual Learning for Visual Tracking. SemEval-2017 Task 8: RumourEval: Determining rumour veracity and support for rumours. 3D Shape Classific …
Probabilistic Generative Adversarial Networks
| Title | Probabilistic Generative Adversarial Networks |
| Authors | Hamid Eghbal-zadeh, Gerhard Widmer |
| Abstract | We introduce the Probabilistic Generative Adversarial Network (PGAN), a new GAN variant based on a new kind of objective function. The central idea is to integrate a probabilistic model (a Gaussian Mixture Model, in our case) into the GAN framework which supports a new kind of loss function (based on likelihood rather than classification loss), and at the same time gives a meaningful measure of the quality of the outputs generated by the network. Experiments with MNIST show that the model learns to generate realistic images, and at the same time computes likelihoods that are correlated with the quality of the generated images. We show that PGAN is better able to cope with instability problems that are usually observed in the GAN training procedure. We investigate this from three aspects: the probability landscape of the discriminator, gradients of the generator, and the perfect discriminator problem. |
| Tasks | |
| Published | 2017-08-06 |
| URL | http://arxiv.org/abs/1708.01886v1 |
| http://arxiv.org/pdf/1708.01886v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-generative-adversarial-networks |
| Repo | |
| Framework | |
On the EM-Tau algorithm: a new EM-style algorithm with partial E-steps
| Title | On the EM-Tau algorithm: a new EM-style algorithm with partial E-steps |
| Authors | Val Andrei Fajardo, Jiaxi Liang |
| Abstract | The EM algorithm is one of many important tools in the field of statistics. While often used for imputing missing data, its widespread applications include other common statistical tasks, such as clustering. In clustering, the EM algorithm assumes a parametric distribution for the clusters, whose parameters are estimated through a novel iterative procedure that is based on the theory of maximum likelihood. However, one major drawback of the EM algorithm, that renders it impractical especially when working with large datasets, is that it often requires several passes of the data before convergence. In this paper, we introduce a new EM-style algorithm that implements a novel policy for performing partial E-steps. We call the new algorithm the EM-Tau algorithm, which can approximate the traditional EM algorithm with high accuracy but with only a fraction of the running time. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07814v1 |
| http://arxiv.org/pdf/1711.07814v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-em-tau-algorithm-a-new-em-style |
| Repo | |
| Framework | |
A Frequency Domain Neural Network for Fast Image Super-resolution
| Title | A Frequency Domain Neural Network for Fast Image Super-resolution |
| Authors | Junxuan Li, Shaodi You, Antonio Robles-Kelly |
| Abstract | In this paper, we present a frequency domain neural network for image super-resolution. The network employs the convolution theorem so as to cast convolutions in the spatial domain as products in the frequency domain. Moreover, the non-linearity in deep nets, often achieved by a rectifier unit, is here cast as a convolution in the frequency domain. This not only yields a network which is very computationally efficient at testing but also one whose parameters can all be learnt accordingly. The network can be trained using back propagation and is devoid of complex numbers due to the use of the Hartley transform as an alternative to the Fourier transform. Moreover, the network is potentially applicable to other problems elsewhere in computer vision and image processing which are often cast in the frequency domain. We show results on super-resolution and compare against alternatives elsewhere in the literature. In our experiments, our network is one to two orders of magnitude faster than the alternatives with an imperceptible loss of performance. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2017-12-08 |
| URL | http://arxiv.org/abs/1712.03037v1 |
| http://arxiv.org/pdf/1712.03037v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-frequency-domain-neural-network-for-fast |
| Repo | |
| Framework | |
CREST: Convolutional Residual Learning for Visual Tracking
| Title | CREST: Convolutional Residual Learning for Visual Tracking |
| Authors | Yibing Song, Chao Ma, Lijun Gong, Jiawei Zhang, Rynson Lau, Ming-Hsuan Yang |
| Abstract | Discriminative correlation filters (DCFs) have been shown to perform superiorly in visual tracking. They only need a small set of training samples from the initial frame to generate an appearance model. However, existing DCFs learn the filters separately from feature extraction, and update these filters using a moving average operation with an empirical weight. These DCF trackers hardly benefit from the end-to-end training. In this paper, we propose the CREST algorithm to reformulate DCFs as a one-layer convolutional neural network. Our method integrates feature extraction, response map generation as well as model update into the neural networks for an end-to-end training. To reduce model degradation during online update, we apply residual learning to take appearance changes into account. Extensive experiments on the benchmark datasets demonstrate that our CREST tracker performs favorably against state-of-the-art trackers. |
| Tasks | Visual Tracking |
| Published | 2017-08-01 |
| URL | http://arxiv.org/abs/1708.00225v1 |
| http://arxiv.org/pdf/1708.00225v1.pdf | |
| PWC | https://paperswithcode.com/paper/crest-convolutional-residual-learning-for |
| Repo | |
| Framework | |
SemEval-2017 Task 8: RumourEval: Determining rumour veracity and support for rumours
| Title | SemEval-2017 Task 8: RumourEval: Determining rumour veracity and support for rumours |
| Authors | Leon Derczynski, Kalina Bontcheva, Maria Liakata, Rob Procter, Geraldine Wong Sak Hoi, Arkaitz Zubiaga |
| Abstract | Media is full of false claims. Even Oxford Dictionaries named “post-truth” as the word of 2016. This makes it more important than ever to build systems that can identify the veracity of a story, and the kind of discourse there is around it. RumourEval is a SemEval shared task that aims to identify and handle rumours and reactions to them, in text. We present an annotation scheme, a large dataset covering multiple topics - each having their own families of claims and replies - and use these to pose two concrete challenges as well as the results achieved by participants on these challenges. |
| Tasks | Rumour Detection |
| Published | 2017-04-20 |
| URL | http://arxiv.org/abs/1704.05972v1 |
| http://arxiv.org/pdf/1704.05972v1.pdf | |
| PWC | https://paperswithcode.com/paper/semeval-2017-task-8-rumoureval-determining |
| Repo | |
| Framework | |
3D Shape Classification Using Collaborative Representation based Projections
| Title | 3D Shape Classification Using Collaborative Representation based Projections |
| Authors | F. Fotopoulou, S. Oikonomou, A. Papathanasiou, G. Economou, S. Fotopoulos |
| Abstract | A novel 3D shape classification scheme, based on collaborative representation learning, is investigated in this work. A data-driven feature-extraction procedure, taking the form of a simple projection operator, is in the core of our methodology. Provided a shape database, a graph encapsulating the structural relationships among all the available shapes, is first constructed and then employed in defining low-dimensional sparse projections. The recently introduced method of CRPs (collaborative representation based projections), which is based on L2-Graph, is the first variant that is included towards this end. A second algorithm, that particularizes the CRPs to shape descriptors that are inherently nonnegative, is also introduced as potential alternative. In both cases, the weights in the graph reflecting the database structure are calculated so as to approximate each shape as a sparse linear combination of the remaining dataset objects. By way of solving a generalized eigenanalysis problem, a linear matrix operator is designed that will act as the feature extractor. Two popular, inherently high dimensional descriptors, namely ShapeDNA and Global Point Signature (GPS), are employed in our experimentations with SHREC10, SHREC11 and SCHREC 15 datasets, where shape recognition is cast as a multi-class classification problem that is tackled by means of an SVM (support vector machine) acting within the reduced dimensional space of the crafted projections. The results are very promising and outperform state of the art methods, providing evidence about the highly discriminative nature of the introduced 3D shape representations. |
| Tasks | Representation Learning |
| Published | 2017-11-13 |
| URL | http://arxiv.org/abs/1711.04875v2 |
| http://arxiv.org/pdf/1711.04875v2.pdf | |
| PWC | https://paperswithcode.com/paper/3d-shape-classification-using-collaborative |
| Repo | |
| Framework | |
Agent-Agnostic Human-in-the-Loop Reinforcement Learning
| Title | Agent-Agnostic Human-in-the-Loop Reinforcement Learning |
| Authors | David Abel, John Salvatier, Andreas Stuhlmüller, Owain Evans |
| Abstract | Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to learn efficiently in complex environments; many of these methods tailor the teacher’s guidance to agents with a particular representation or underlying learning scheme, offering effective but specialized teaching procedures. In this work, we explore protocol programs, an agent-agnostic schema for Human-in-the-Loop Reinforcement Learning. Our goal is to incorporate the beneficial properties of a human teacher into Reinforcement Learning without making strong assumptions about the inner workings of the agent. We show how to represent existing approaches such as action pruning, reward shaping, and training in simulation as special cases of our schema and conduct preliminary experiments on simple domains. |
| Tasks | |
| Published | 2017-01-15 |
| URL | http://arxiv.org/abs/1701.04079v1 |
| http://arxiv.org/pdf/1701.04079v1.pdf | |
| PWC | https://paperswithcode.com/paper/agent-agnostic-human-in-the-loop |
| Repo | |
| Framework | |
Detection and Resolution of Rumours in Social Media: A Survey
| Title | Detection and Resolution of Rumours in Social Media: A Survey |
| Authors | Arkaitz Zubiaga, Ahmet Aker, Kalina Bontcheva, Maria Liakata, Rob Procter |
| Abstract | Despite the increasing use of social media platforms for information and news gathering, its unmoderated nature often leads to the emergence and spread of rumours, i.e. pieces of information that are unverified at the time of posting. At the same time, the openness of social media platforms provides opportunities to study how users share and discuss rumours, and to explore how natural language processing and data mining techniques may be used to find ways of determining their veracity. In this survey we introduce and discuss two types of rumours that circulate on social media; long-standing rumours that circulate for long periods of time, and newly-emerging rumours spawned during fast-paced events such as breaking news, where reports are released piecemeal and often with an unverified status in their early stages. We provide an overview of research into social media rumours with the ultimate goal of developing a rumour classification system that consists of four components: rumour detection, rumour tracking, rumour stance classification and rumour veracity classification. We delve into the approaches presented in the scientific literature for the development of each of these four components. We summarise the efforts and achievements so far towards the development of rumour classification systems and conclude with suggestions for avenues for future research in social media mining for detection and resolution of rumours. |
| Tasks | Rumour Detection |
| Published | 2017-04-03 |
| URL | http://arxiv.org/abs/1704.00656v3 |
| http://arxiv.org/pdf/1704.00656v3.pdf | |
| PWC | https://paperswithcode.com/paper/detection-and-resolution-of-rumours-in-social |
| Repo | |
| Framework | |
Generating Music Medleys via Playing Music Puzzle Games
| Title | Generating Music Medleys via Playing Music Puzzle Games |
| Authors | Yu-Siang Huang, Szu-Yu Chou, Yi-Hsuan Yang |
| Abstract | Generating music medleys is about finding an optimal permutation of a given set of music clips. Toward this goal, we propose a self-supervised learning task, called the music puzzle game, to train neural network models to learn the sequential patterns in music. In essence, such a game requires machines to correctly sort a few multisecond music fragments. In the training stage, we learn the model by sampling multiple non-overlapping fragment pairs from the same songs and seeking to predict whether a given pair is consecutive and is in the correct chronological order. For testing, we design a number of puzzle games with different difficulty levels, the most difficult one being music medley, which requiring sorting fragments from different songs. On the basis of state-of-the-art Siamese convolutional network, we propose an improved architecture that learns to embed frame-level similarity scores computed from the input fragment pairs to a common space, where fragment pairs in the correct order can be more easily identified. Our result shows that the resulting model, dubbed as the similarity embedding network (SEN), performs better than competing models across different games, including music jigsaw puzzle, music sequencing, and music medley. Example results can be found at our project website, https://remyhuang.github.io/DJnet. |
| Tasks | |
| Published | 2017-09-13 |
| URL | http://arxiv.org/abs/1709.04384v2 |
| http://arxiv.org/pdf/1709.04384v2.pdf | |
| PWC | https://paperswithcode.com/paper/generating-music-medleys-via-playing-music |
| Repo | |
| Framework | |
The Incremental Multiresolution Matrix Factorization Algorithm
| Title | The Incremental Multiresolution Matrix Factorization Algorithm |
| Authors | Vamsi K. Ithapu, Risi Kondor, Sterling C. Johnson, Vikas Singh |
| Abstract | Multiresolution analysis and matrix factorization are foundational tools in computer vision. In this work, we study the interface between these two distinct topics and obtain techniques to uncover hierarchical block structure in symmetric matrices – an important aspect in the success of many vision problems. Our new algorithm, the incremental multiresolution matrix factorization, uncovers such structure one feature at a time, and hence scales well to large matrices. We describe how this multiscale analysis goes much farther than what a direct global factorization of the data can identify. We evaluate the efficacy of the resulting factorizations for relative leveraging within regression tasks using medical imaging data. We also use the factorization on representations learned by popular deep networks, providing evidence of their ability to infer semantic relationships even when they are not explicitly trained to do so. We show that this algorithm can be used as an exploratory tool to improve the network architecture, and within numerous other settings in vision. |
| Tasks | |
| Published | 2017-05-16 |
| URL | http://arxiv.org/abs/1705.05804v1 |
| http://arxiv.org/pdf/1705.05804v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-incremental-multiresolution-matrix |
| Repo | |
| Framework | |
On Usage of Autoencoders and Siamese Networks for Online Handwritten Signature Verification
| Title | On Usage of Autoencoders and Siamese Networks for Online Handwritten Signature Verification |
| Authors | Kian Ahrabian, Bagher Babaali |
| Abstract | In this paper, we propose a novel writer-independent global feature extraction framework for the task of automatic signature verification which aims to make robust systems for automatically distinguishing negative and positive samples. Our method consists of an autoencoder for modeling the sample space into a fixed length latent space and a Siamese Network for classifying the fixed-length samples obtained from the autoencoder based on the reference samples of a subject as being “Genuine” or “Forged.” During our experiments, usage of Attention Mechanism and applying Downsampling significantly improved the accuracy of the proposed framework. We evaluated our proposed framework using SigWiComp2013 Japanese and GPDSsyntheticOnLineOffLineSignature datasets. On the SigWiComp2013 Japanese dataset, we achieved 8.65% EER that means 1.2% relative improvement compared to the best-reported result. Furthermore, on the GPDSsyntheticOnLineOffLineSignature dataset, we achieved average EERs of 0.13%, 0.12%, 0.21% and 0.25% respectively for 150, 300, 1000 and 2000 test subjects which indicates improvement of relative EER on the best-reported result by 95.67%, 95.26%, 92.9% and 91.52% respectively. Apart from the accuracy gain, because of the nature of our proposed framework which is based on neural networks and consequently is as simple as some consecutive matrix multiplications, it has less computational cost than conventional methods such as DTW and could be used concurrently on devices such as GPU, TPU, etc. |
| Tasks | |
| Published | 2017-12-07 |
| URL | http://arxiv.org/abs/1712.02781v2 |
| http://arxiv.org/pdf/1712.02781v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-usage-of-autoencoders-and-siamese-networks |
| Repo | |
| Framework | |
Using Noisy Extractions to Discover Causal Knowledge
| Title | Using Noisy Extractions to Discover Causal Knowledge |
| Authors | Dhanya Sridhar, Jay Pujara, Lise Getoor |
| Abstract | Knowledge bases (KB) constructed through information extraction from text play an important role in query answering and reasoning. In this work, we study a particular reasoning task, the problem of discovering causal relationships between entities, known as causal discovery. There are two contrasting types of approaches to discovering causal knowledge. One approach attempts to identify causal relationships from text using automatic extraction techniques, while the other approach infers causation from observational data. However, extractions alone are often insufficient to capture complex patterns and full observational data is expensive to obtain. We introduce a probabilistic method for fusing noisy extractions with observational data to discover causal knowledge. We propose a principled approach that uses the probabilistic soft logic (PSL) framework to encode well-studied constraints to recover long-range patterns and consistent predictions, while cheaply acquired extractions provide a proxy for unseen observations. We apply our method gene regulatory networks and show the promise of exploiting KB signals in causal discovery, suggesting a critical, new area of research. |
| Tasks | Causal Discovery |
| Published | 2017-11-16 |
| URL | http://arxiv.org/abs/1711.05900v1 |
| http://arxiv.org/pdf/1711.05900v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-noisy-extractions-to-discover-causal |
| Repo | |
| Framework | |
Parallel Implementation of Efficient Search Schemes for the Inference of Cancer Progression Models
| Title | Parallel Implementation of Efficient Search Schemes for the Inference of Cancer Progression Models |
| Authors | Daniele Ramazzotti, Marco S. Nobile, Paolo Cazzaniga, Giancarlo Mauri, Marco Antoniotti |
| Abstract | The emergence and development of cancer is a consequence of the accumulation over time of genomic mutations involving a specific set of genes, which provides the cancer clones with a functional selective advantage. In this work, we model the order of accumulation of such mutations during the progression, which eventually leads to the disease, by means of probabilistic graphic models, i.e., Bayesian Networks (BNs). We investigate how to perform the task of learning the structure of such BNs, according to experimental evidence, adopting a global optimization meta-heuristics. In particular, in this work we rely on Genetic Algorithms, and to strongly reduce the execution time of the inference – which can also involve multiple repetitions to collect statistically significant assessments of the data – we distribute the calculations using both multi-threading and a multi-node architecture. The results show that our approach is characterized by good accuracy and specificity; we also demonstrate its feasibility, thanks to a 84x reduction of the overall execution time with respect to a traditional sequential implementation. |
| Tasks | |
| Published | 2017-03-08 |
| URL | http://arxiv.org/abs/1703.03038v1 |
| http://arxiv.org/pdf/1703.03038v1.pdf | |
| PWC | https://paperswithcode.com/paper/parallel-implementation-of-efficient-search |
| Repo | |
| Framework | |
Stability and Generalization of Learning Algorithms that Converge to Global Optima
| Title | Stability and Generalization of Learning Algorithms that Converge to Global Optima |
| Authors | Zachary Charles, Dimitris Papailiopoulos |
| Abstract | We establish novel generalization bounds for learning algorithms that converge to global minima. We do so by deriving black-box stability results that only depend on the convergence of a learning algorithm and the geometry around the minimizers of the loss function. The results are shown for nonconvex loss functions satisfying the Polyak-{\L}ojasiewicz (PL) and the quadratic growth (QG) conditions. We further show that these conditions arise for some neural networks with linear activations. We use our black-box results to establish the stability of optimization algorithms such as stochastic gradient descent (SGD), gradient descent (GD), randomized coordinate descent (RCD), and the stochastic variance reduced gradient method (SVRG), in both the PL and the strongly convex setting. Our results match or improve state-of-the-art generalization bounds and can easily be extended to similar optimization algorithms. Finally, we show that although our results imply comparable stability for SGD and GD in the PL setting, there exist simple neural networks with multiple local minima where SGD is stable but GD is not. |
| Tasks | |
| Published | 2017-10-23 |
| URL | http://arxiv.org/abs/1710.08402v1 |
| http://arxiv.org/pdf/1710.08402v1.pdf | |
| PWC | https://paperswithcode.com/paper/stability-and-generalization-of-learning |
| Repo | |
| Framework | |
Optimal Combination of Image Denoisers
| Title | Optimal Combination of Image Denoisers |
| Authors | Joon Hee Choi, Omar Elgendy, Stanley H. Chan |
| Abstract | Given a set of image denoisers, each having a different denoising capability, is there a provably optimal way of combining these denoisers to produce an overall better result? An answer to this question is fundamental to designing an ensemble of weak estimators for complex scenes. In this paper, we present an optimal combination scheme by leveraging deep neural networks and convex optimization. The proposed framework, called the Consensus Neural Network (CsNet), introduces three new concepts in image denoising: (1) A provably optimal procedure to combine the denoised outputs via convex optimization; (2) A deep neural network to estimate the mean squared error (MSE) of denoised images without needing the ground truths; (3) An image boosting procedure using a deep neural network to improve contrast and to recover lost details of the combined images. Experimental results show that CsNet can consistently improve denoising performance for both deterministic and neural network denoisers. |
| Tasks | Denoising, Image Denoising |
| Published | 2017-11-17 |
| URL | http://arxiv.org/abs/1711.06712v4 |
| http://arxiv.org/pdf/1711.06712v4.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-combination-of-image-denoisers |
| Repo | |
| Framework | |
