Paper Group AWR 67
Computational Historical Linguistics. Heterogeneous multireference alignment for images with application to 2-D classification in single particle reconstruction. A Machine Learning Framework for Stock Selection. AVID: Adversarial Visual Irregularity Detection. Backprop-Q: Generalized Backpropagation for Stochastic Computation Graphs. Multi-modal Cy …
Computational Historical Linguistics
| Title | Computational Historical Linguistics |
| Authors | Gerhard Jäger |
| Abstract | Computational approaches to historical linguistics have been proposed since half a century. Within the last decade, this line of research has received a major boost, owing both to the transfer of ideas and software from computational biology and to the release of several large electronic data resources suitable for systematic comparative work. In this article, some of the central research topic of this new wave of computational historical linguistics are introduced and discussed. These are automatic assessment of genetic relatedness, automatic cognate detection, phylogenetic inference and ancestral state reconstruction. They will be demonstrated by means of a case study of automatically reconstructing a Proto-Romance word list from lexical data of 50 modern Romance languages and dialects. |
| Tasks | |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.08099v1 |
| http://arxiv.org/pdf/1805.08099v1.pdf | |
| PWC | https://paperswithcode.com/paper/computational-historical-linguistics |
| Repo | https://github.com/gerhardJaeger/protoRomance |
| Framework | none |
Heterogeneous multireference alignment for images with application to 2-D classification in single particle reconstruction
| Title | Heterogeneous multireference alignment for images with application to 2-D classification in single particle reconstruction |
| Authors | Chao Ma, Tamir Bendory, Nicolas Boumal, Fred Sigworth, Amit Singer |
| Abstract | Motivated by the task of 2-D classification in single particle reconstruction by cryo-electron microscopy (cryo-EM), we consider the problem of heterogeneous multireference alignment of images. In this problem, the goal is to estimate a (typically small) set of target images from a (typically large) collection of observations. Each observation is a rotated, noisy version of one of the target images. For each individual observation, neither the rotation nor which target image has been rotated are known. As the noise level in cryo-EM data is high, clustering the observations and estimating individual rotations is challenging. We propose a framework to estimate the target images directly from the observations, completely bypassing the need to cluster or register the images. The framework consists of two steps. First, we estimate rotation-invariant features of the images, such as the bispectrum. These features can be estimated to any desired accuracy, at any noise level, provided sufficiently many observations are collected. Then, we estimate the images from the invariant features. Numerical experiments on synthetic cryo-EM datasets demonstrate the effectiveness of the method. Ultimately, we outline future developments required to apply this method to experimental data. |
| Tasks | |
| Published | 2018-10-12 |
| URL | https://arxiv.org/abs/1811.10382v2 |
| https://arxiv.org/pdf/1811.10382v2.pdf | |
| PWC | https://paperswithcode.com/paper/heterogeneous-multireference-alignment-for |
| Repo | https://github.com/chaom1026/2DhMRA |
| Framework | none |
A Machine Learning Framework for Stock Selection
| Title | A Machine Learning Framework for Stock Selection |
| Authors | XingYu Fu, JinHong Du, YiFeng Guo, MingWen Liu, Tao Dong, XiuWen Duan |
| Abstract | This paper demonstrates how to apply machine learning algorithms to distinguish good stocks from the bad stocks. To this end, we construct 244 technical and fundamental features to characterize each stock, and label stocks according to their ranking with respect to the return-to-volatility ratio. Algorithms ranging from traditional statistical learning methods to recently popular deep learning method, e.g. Logistic Regression (LR), Random Forest (RF), Deep Neural Network (DNN), and the Stacking, are trained to solve the classification task. Genetic Algorithm (GA) is also used to implement feature selection. The effectiveness of the stock selection strategy is validated in Chinese stock market in both statistical and practical aspects, showing that: 1) Stacking outperforms other models reaching an AUC score of 0.972; 2) Genetic Algorithm picks a subset of 114 features and the prediction performances of all models remain almost unchanged after the selection procedure, which suggests some features are indeed redundant; 3) LR and DNN are radical models; RF is risk-neutral model; Stacking is somewhere between DNN and RF. 4) The portfolios constructed by our models outperform market average in back tests. |
| Tasks | Feature Selection |
| Published | 2018-06-05 |
| URL | http://arxiv.org/abs/1806.01743v2 |
| http://arxiv.org/pdf/1806.01743v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-machine-learning-framework-for-stock |
| Repo | https://github.com/fxy96/Stock-Selection-a-Framework |
| Framework | tf |
AVID: Adversarial Visual Irregularity Detection
| Title | AVID: Adversarial Visual Irregularity Detection |
| Authors | Mohammad Sabokrou, Masoud Pourreza, Mohsen Fayyaz, Rahim Entezari, Mahmood Fathy, Jürgen Gall, Ehsan Adeli |
| Abstract | Real-time detection of irregularities in visual data is very invaluable and useful in many prospective applications including surveillance, patient monitoring systems, etc. With the surge of deep learning methods in the recent years, researchers have tried a wide spectrum of methods for different applications. However, for the case of irregularity or anomaly detection in videos, training an end-to-end model is still an open challenge, since often irregularity is not well-defined and there are not enough irregular samples to use during training. In this paper, inspired by the success of generative adversarial networks (GANs) for training deep models in unsupervised or self-supervised settings, we propose an end-to-end deep network for detection and fine localization of irregularities in videos (and images). Our proposed architecture is composed of two networks, which are trained in competing with each other while collaborating to find the irregularity. One network works as a pixel-level irregularity Inpainter, and the other works as a patch-level Detector. After an adversarial self-supervised training, in which I tries to fool D into accepting its inpainted output as regular (normal), the two networks collaborate to detect and fine-segment the irregularity in any given testing video. Our results on three different datasets show that our method can outperform the state-of-the-art and fine-segment the irregularity. |
| Tasks | Anomaly Detection |
| Published | 2018-05-24 |
| URL | http://arxiv.org/abs/1805.09521v2 |
| http://arxiv.org/pdf/1805.09521v2.pdf | |
| PWC | https://paperswithcode.com/paper/avid-adversarial-visual-irregularity |
| Repo | https://github.com/cross32768/AVID-Adversarial-Visual-Irregularity-Detection |
| Framework | none |
Backprop-Q: Generalized Backpropagation for Stochastic Computation Graphs
| Title | Backprop-Q: Generalized Backpropagation for Stochastic Computation Graphs |
| Authors | Xiaoran Xu, Songpeng Zu, Yuan Zhang, Hanning Zhou, Wei Feng |
| Abstract | In real-world scenarios, it is appealing to learn a model carrying out stochastic operations internally, known as stochastic computation graphs (SCGs), rather than learning a deterministic mapping. However, standard backpropagation is not applicable to SCGs. We attempt to address this issue from the angle of cost propagation, with local surrogate costs, called Q-functions, constructed and learned for each stochastic node in an SCG. Then, the SCG can be trained based on these surrogate costs using standard backpropagation. We propose the entire framework as a solution to generalize backpropagation for SCGs, which resembles an actor-critic architecture but based on a graph. For broad applicability, we study a variety of SCG structures from one cost to multiple costs. We utilize recent advances in reinforcement learning (RL) and variational Bayes (VB), such as off-policy critic learning and unbiased-and-low-variance gradient estimation, and review them in the context of SCGs. The generalized backpropagation extends transported learning signals beyond gradients between stochastic nodes while preserving the benefit of backpropagating gradients through deterministic nodes. Experimental suggestions and concerns are listed to help design and test any specific model using this framework. |
| Tasks | |
| Published | 2018-07-25 |
| URL | http://arxiv.org/abs/1807.09511v2 |
| http://arxiv.org/pdf/1807.09511v2.pdf | |
| PWC | https://paperswithcode.com/paper/backprop-q-generalized-backpropagation-for |
| Repo | https://github.com/netpaladinx/experiments-for-Backprop-Q |
| Framework | none |
Multi-modal Cycle-consistent Generalized Zero-Shot Learning
| Title | Multi-modal Cycle-consistent Generalized Zero-Shot Learning |
| Authors | Rafael Felix, B. G. Vijay Kumar, Ian Reid, Gustavo Carneiro |
| Abstract | In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes, while testing uses the visual representations of the seen and unseen classes. Current methods address GZSL by learning a transformation from the visual to the semantic space, exploring the assumption that the distribution of classes in the semantic and visual spaces is relatively similar. Such methods tend to transform unseen testing visual representations into one of the seen classes’ semantic features instead of the semantic features of the correct unseen class, resulting in low accuracy GZSL classification. Recently, generative adversarial networks (GAN) have been explored to synthesize visual representations of the unseen classes from their semantic features - the synthesized representations of the seen and unseen classes are then used to train the GZSL classifier. This approach has been shown to boost GZSL classification accuracy, however, there is no guarantee that synthetic visual representations can generate back their semantic feature in a multi-modal cycle-consistent manner. This constraint can result in synthetic visual representations that do not represent well their semantic features. In this paper, we propose the use of such constraint based on a new regularization for the GAN training that forces the generated visual features to reconstruct their original semantic features. Once our model is trained with this multi-modal cycle-consistent semantic compatibility, we can then synthesize more representative visual representations for the seen and, more importantly, for the unseen classes. Our proposed approach shows the best GZSL classification results in the field in several publicly available datasets. |
| Tasks | Zero-Shot Learning |
| Published | 2018-08-01 |
| URL | http://arxiv.org/abs/1808.00136v2 |
| http://arxiv.org/pdf/1808.00136v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-cycle-consistent-generalized-zero |
| Repo | https://github.com/rfelixmg/frwgan-eccv18 |
| Framework | tf |
Classifier and Exemplar Synthesis for Zero-Shot Learning
| Title | Classifier and Exemplar Synthesis for Zero-Shot Learning |
| Authors | Soravit Changpinyo, Wei-Lun Chao, Boqing Gong, Fei Sha |
| Abstract | Zero-shot learning (ZSL) enables solving a task without the need to see its examples. In this paper, we propose two ZSL frameworks that learn to synthesize parameters for novel unseen classes. First, we propose to cast the problem of ZSL as learning manifold embeddings from graphs composed of object classes, leading to a flexible approach that synthesizes “classifiers” for the unseen classes. Then, we define an auxiliary task of synthesizing “exemplars” for the unseen classes to be used as an automatic denoising mechanism for any existing ZSL approaches or as an effective ZSL model by itself. On five visual recognition benchmark datasets, we demonstrate the superior performances of our proposed frameworks in various scenarios of both conventional and generalized ZSL. Finally, we provide valuable insights through a series of empirical analyses, among which are a comparison of semantic representations on the full ImageNet benchmark as well as a comparison of metrics used in generalized ZSL. Our code and data are publicly available at https://github.com/pujols/Zero-shot-learning-journal |
| Tasks | Denoising, Zero-Shot Learning |
| Published | 2018-12-16 |
| URL | https://arxiv.org/abs/1812.06423v2 |
| https://arxiv.org/pdf/1812.06423v2.pdf | |
| PWC | https://paperswithcode.com/paper/classifier-and-exemplar-synthesis-for-zero |
| Repo | https://github.com/pujols/Zero-shot-learning-journal |
| Framework | none |
Few-shot classification in Named Entity Recognition Task
| Title | Few-shot classification in Named Entity Recognition Task |
| Authors | Alexander Fritzler, Varvara Logacheva, Maksim Kretov |
| Abstract | For many natural language processing (NLP) tasks the amount of annotated data is limited. This urges a need to apply semi-supervised learning techniques, such as transfer learning or meta-learning. In this work we tackle Named Entity Recognition (NER) task using Prototypical Network - a metric learning technique. It learns intermediate representations of words which cluster well into named entity classes. This property of the model allows classifying words with extremely limited number of training examples, and can potentially be used as a zero-shot learning method. By coupling this technique with transfer learning we achieve well-performing classifiers trained on only 20 instances of a target class. |
| Tasks | Meta-Learning, Metric Learning, Named Entity Recognition, Transfer Learning, Zero-Shot Learning |
| Published | 2018-12-14 |
| URL | http://arxiv.org/abs/1812.06158v1 |
| http://arxiv.org/pdf/1812.06158v1.pdf | |
| PWC | https://paperswithcode.com/paper/few-shot-classification-in-named-entity |
| Repo | https://github.com/Fritz449/ProtoNER |
| Framework | pytorch |
Generative Dual Adversarial Network for Generalized Zero-shot Learning
| Title | Generative Dual Adversarial Network for Generalized Zero-shot Learning |
| Authors | He Huang, Changhu Wang, Philip S. Yu, Chang-Dong Wang |
| Abstract | This paper studies the problem of generalized zero-shot learning which requires the model to train on image-label pairs from some seen classes and test on the task of classifying new images from both seen and unseen classes. Most previous models try to learn a fixed one-directional mapping between visual and semantic space, while some recently proposed generative methods try to generate image features for unseen classes so that the zero-shot learning problem becomes a traditional fully-supervised classification problem. In this paper, we propose a novel model that provides a unified framework for three different approaches: visual-> semantic mapping, semantic->visual mapping, and metric learning. Specifically, our proposed model consists of a feature generator that can generate various visual features given class embeddings as input, a regressor that maps each visual feature back to its corresponding class embedding, and a discriminator that learns to evaluate the closeness of an image feature and a class embedding. All three components are trained under the combination of cyclic consistency loss and dual adversarial loss. Experimental results show that our model not only preserves higher accuracy in classifying images from seen classes, but also performs better than existing state-of-the-art models in in classifying images from unseen classes. |
| Tasks | Metric Learning, Zero-Shot Learning |
| Published | 2018-11-12 |
| URL | https://arxiv.org/abs/1811.04857v4 |
| https://arxiv.org/pdf/1811.04857v4.pdf | |
| PWC | https://paperswithcode.com/paper/generative-dual-adversarial-network-for |
| Repo | https://github.com/stevehuanghe/GDAN |
| Framework | pytorch |
A General Deep Learning Framework for Network Reconstruction and Dynamics Learning
| Title | A General Deep Learning Framework for Network Reconstruction and Dynamics Learning |
| Authors | Zhang Zhang, Yi Zhao, Jing Liu, Shuo Wang, Ruyi Tao, Ruyue Xin, Jiang Zhang |
| Abstract | Many complex processes can be viewed as dynamical systems on networks. However, in real cases, only the performances of the system are known, the network structure and the dynamical rules are not observed. Therefore, recovering latent network structure and dynamics from observed time series data are important tasks because it may help us to open the black box, and even to build up the model of a complex system automatically. Although this problem hosts a wealth of potential applications in biology, earth science, and epidemics etc., conventional methods have limitations. In this work, we introduce a new framework, Gumbel Graph Network (GGN), which is a model-free, data-driven deep learning framework to accomplish the reconstruction of both network connections and the dynamics on it. Our model consists of two jointly trained parts: a network generator that generating a discrete network with the Gumbel Softmax technique; and a dynamics learner that utilizing the generated network and one-step trajectory value to predict the states in future steps. We exhibit the universality of our framework on different kinds of time-series data: with the same structure, our model can be trained to accurately recover the network structure and predict future states on continuous, discrete, and binary dynamics, and outperforms competing network reconstruction methods. |
| Tasks | Time Series |
| Published | 2018-12-30 |
| URL | https://arxiv.org/abs/1812.11482v3 |
| https://arxiv.org/pdf/1812.11482v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-deep-learning-framework-for-network |
| Repo | https://github.com/bnusss/GGN |
| Framework | pytorch |
Supervised Policy Update for Deep Reinforcement Learning
| Title | Supervised Policy Update for Deep Reinforcement Learning |
| Authors | Quan Vuong, Yiming Zhang, Keith W. Ross |
| Abstract | We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the non-parameterized proximal policy space. Using supervised regression, it then converts the optimal non-parameterized policy to a parameterized policy, from which it draws new samples. The methodology is general in that it applies to both discrete and continuous action spaces, and can handle a wide variety of proximity constraints for the non-parameterized optimization problem. We show how the Natural Policy Gradient and Trust Region Policy Optimization (NPG/TRPO) problems, and the Proximal Policy Optimization (PPO) problem can be addressed by this methodology. The SPU implementation is much simpler than TRPO. In terms of sample efficiency, our extensive experiments show SPU outperforms TRPO in Mujoco simulated robotic tasks and outperforms PPO in Atari video game tasks. |
| Tasks | |
| Published | 2018-05-29 |
| URL | http://arxiv.org/abs/1805.11706v4 |
| http://arxiv.org/pdf/1805.11706v4.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-policy-update-for-deep |
| Repo | https://github.com/quanvuong/Supervised_Policy_Update |
| Framework | tf |
Efficient Concept Induction for Description Logics
| Title | Efficient Concept Induction for Description Logics |
| Authors | Md Kamruzzaman Sarker, Pascal Hitzler |
| Abstract | Concept Induction refers to the problem of creating complex Description Logic class descriptions (i.e., TBox axioms) from instance examples (i.e., ABox data). In this paper we look particularly at the case where both a set of positive and a set of negative instances are given, and complex class expressions are sought under which the positive but not the negative examples fall. Concept induction has found applications in ontology engineering, but existing algorithms have fundamental performance issues in some scenarios, mainly because a high number of invokations of an external Description Logic reasoner is usually required. In this paper we present a new algorithm for this problem which drastically reduces the number of reasoner invokations needed. While this comes at the expense of a more limited traversal of the search space, we show that our approach improves execution times by up to several orders of magnitude, while output correctness, measured in the amount of correct coverage of the input instances, remains reasonably high in many cases. Our approach thus should provide a strong alternative to existing systems, in particular in settings where other systems are prohibitively slow. |
| Tasks | |
| Published | 2018-12-08 |
| URL | http://arxiv.org/abs/1812.03243v1 |
| http://arxiv.org/pdf/1812.03243v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-concept-induction-for-description |
| Repo | https://github.com/md-k-sarker/ecii-expr |
| Framework | none |
Animating Arbitrary Objects via Deep Motion Transfer
| Title | Animating Arbitrary Objects via Deep Motion Transfer |
| Authors | Aliaksandr Siarohin, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe |
| Abstract | This paper introduces a novel deep learning framework for image animation. Given an input image with a target object and a driving video sequence depicting a moving object, our framework generates a video in which the target object is animated according to the driving sequence. This is achieved through a deep architecture that decouples appearance and motion information. Our framework consists of three main modules: (i) a Keypoint Detector unsupervisely trained to extract object keypoints, (ii) a Dense Motion prediction network for generating dense heatmaps from sparse keypoints, in order to better encode motion information and (iii) a Motion Transfer Network, which uses the motion heatmaps and appearance information extracted from the input image to synthesize the output frames. We demonstrate the effectiveness of our method on several benchmark datasets, spanning a wide variety of object appearances, and show that our approach outperforms state-of-the-art image animation and video generation methods. Our source code is publicly available. |
| Tasks | Image Animation, motion prediction, Video Generation |
| Published | 2018-12-20 |
| URL | https://arxiv.org/abs/1812.08861v3 |
| https://arxiv.org/pdf/1812.08861v3.pdf | |
| PWC | https://paperswithcode.com/paper/animating-arbitrary-objects-via-deep-motion |
| Repo | https://github.com/AliaksandrSiarohin/monkey-net |
| Framework | pytorch |
Towards the Latent Transcriptome
| Title | Towards the Latent Transcriptome |
| Authors | Assya Trofimov, Francis Dutil, Claude Perreault, Sebastien Lemieux, Yoshua Bengio, Joseph Paul Cohen |
| Abstract | In this work we propose a method to compute continuous embeddings for kmers from raw RNA-seq data, without the need for alignment to a reference genome. The approach uses an RNN to transform kmers of the RNA-seq reads into a 2 dimensional representation that is used to predict abundance of each kmer. We report that our model captures information of both DNA sequence similarity as well as DNA sequence abundance in the embedding latent space, that we call the Latent Transcriptome. We confirm the quality of these vectors by comparing them to known gene sub-structures and report that the latent space recovers exon information from raw RNA-Seq data from acute myeloid leukemia patients. Furthermore we show that this latent space allows the detection of genomic abnormalities such as translocations as well as patient-specific mutations, making this representation space both useful for visualization as well as analysis. |
| Tasks | |
| Published | 2018-10-08 |
| URL | http://arxiv.org/abs/1810.03442v2 |
| http://arxiv.org/pdf/1810.03442v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-the-latent-transcriptome |
| Repo | https://github.com/TrofimovAssya/TheLatentTranscriptome |
| Framework | pytorch |
Scalable Deep Learning Logo Detection
| Title | Scalable Deep Learning Logo Detection |
| Authors | Hang Su, Shaogang Gong, Xiatian Zhu |
| Abstract | Existing logo detection methods usually consider a small number of logo classes and limited images per class with a strong assumption of requiring tedious object bounding box annotations, therefore not scalable to real-world dynamic applications. In this work, we tackle these challenges by exploring the webly data learning principle without the need for exhaustive manual labelling. Specifically, we propose a novel incremental learning approach, called Scalable Logo Self-co-Learning (SL^2), capable of automatically self-discovering informative training images from noisy web data for progressively improving model capability in a cross-model co-learning manner. Moreover, we introduce a very large (2,190,757 images of 194 logo classes) logo dataset “WebLogo-2M” by an automatic web data collection and processing method. Extensive comparative evaluations demonstrate the superiority of the proposed SL^2 method over the state-of-the-art strongly and weakly supervised detection models and contemporary webly data learning approaches. |
| Tasks | |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1803.11417v2 |
| http://arxiv.org/pdf/1803.11417v2.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-deep-learning-logo-detection |
| Repo | https://github.com/synthesio/vision-test |
| Framework | tf |
