May 7, 2019

3148 words 15 mins read

Paper Group ANR 146

A strengthening of rational closure in DLs: reasoning about multiple aspects. Generative Adversarial Nets from a Density Ratio Estimation Perspective. Parametric Exponential Linear Unit for Deep Convolutional Neural Networks. Deeply Aggregated Alternating Minimization for Image Restoration. Pose from Action: Unsupervised Learning of Pose Features b …

A strengthening of rational closure in DLs: reasoning about multiple aspects


Title	A strengthening of rational closure in DLs: reasoning about multiple aspects
Authors	Valentina Gliozzi
Abstract	We propose a logical analysis of the concept of typicality, central in human cognition (Rosch,1978). We start from a previously proposed extension of the basic Description Logic ALC (a computationally tractable fragment of First Order Logic, used to represent concept inclusions and ontologies) with a typicality operator T that allows to consistently represent the attribution to classes of individuals of properties with exceptions (as in the classic example (i) typical birds fly, (ii) penguins are birds but (iii) typical penguins don’t fly). We then strengthen this extension in order to separately reason about the typicality with respect to different aspects (e.g., flying, having nice feather: in the previous example, penguins may not inherit the property of flying, for which they are exceptional, but can nonetheless inherit other properties, such as having nice feather).
Tasks
Published	2016-04-01
URL	http://arxiv.org/abs/1604.00301v1
PDF	http://arxiv.org/pdf/1604.00301v1.pdf
PWC	https://paperswithcode.com/paper/a-strengthening-of-rational-closure-in-dls
Repo
Framework

Generative Adversarial Nets from a Density Ratio Estimation Perspective


Title	Generative Adversarial Nets from a Density Ratio Estimation Perspective
Authors	Masatoshi Uehara, Issei Sato, Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo
Abstract	Generative adversarial networks (GANs) are successful deep generative models. GANs are based on a two-player minimax game. However, the objective function derived in the original motivation is changed to obtain stronger gradients when learning the generator. We propose a novel algorithm that repeats the density ratio estimation and f-divergence minimization. Our algorithm offers a new perspective toward the understanding of GANs and is able to make use of multiple viewpoints obtained in the research of density ratio estimation, e.g. what divergence is stable and relative density ratio is useful.
Tasks
Published	2016-10-10
URL	http://arxiv.org/abs/1610.02920v2
PDF	http://arxiv.org/pdf/1610.02920v2.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-nets-from-a-density
Repo
Framework

Parametric Exponential Linear Unit for Deep Convolutional Neural Networks


Title	Parametric Exponential Linear Unit for Deep Convolutional Neural Networks
Authors	Ludovic Trottier, Philippe Giguère, Brahim Chaib-draa
Abstract	Object recognition is an important task for improving the ability of visual systems to perform complex scene understanding. Recently, the Exponential Linear Unit (ELU) has been proposed as a key component for managing bias shift in Convolutional Neural Networks (CNNs), but defines a parameter that must be set by hand. In this paper, we propose learning a parameterization of ELU in order to learn the proper activation shape at each layer in the CNNs. Our results on the MNIST, CIFAR-10/100 and ImageNet datasets using the NiN, Overfeat, All-CNN and ResNet networks indicate that our proposed Parametric ELU (PELU) has better performances than the non-parametric ELU. We have observed as much as a 7.28% relative error improvement on ImageNet with the NiN network, with only 0.0003% parameter increase. Our visual examination of the non-linear behaviors adopted by Vgg using PELU shows that the network took advantage of the added flexibility by learning different activations at different layers.
Tasks	Object Recognition, Scene Understanding
Published	2016-05-30
URL	http://arxiv.org/abs/1605.09332v4
PDF	http://arxiv.org/pdf/1605.09332v4.pdf
PWC	https://paperswithcode.com/paper/parametric-exponential-linear-unit-for-deep
Repo
Framework

Deeply Aggregated Alternating Minimization for Image Restoration


Title	Deeply Aggregated Alternating Minimization for Image Restoration
Authors	Youngjung Kim, Hyungjoo Jung, Dongbo Min, Kwanghoon Sohn
Abstract	Regularization-based image restoration has remained an active research topic in computer vision and image processing. It often leverages a guidance signal captured in different fields as an additional cue. In this work, we present a general framework for image restoration, called deeply aggregated alternating minimization (DeepAM). We propose to train deep neural network to advance two of the steps in the conventional AM algorithm: proximal mapping and ?- continuation. Both steps are learned from a large dataset in an end-to-end manner. The proposed framework enables the convolutional neural networks (CNNs) to operate as a prior or regularizer in the AM algorithm. We show that our learned regularizer via deep aggregation outperforms the recent data-driven approaches as well as the nonlocalbased methods. The flexibility and effectiveness of our framework are demonstrated in several image restoration tasks, including single image denoising, RGB-NIR restoration, and depth super-resolution.
Tasks	Denoising, Image Denoising, Image Restoration, Super-Resolution
Published	2016-12-20
URL	http://arxiv.org/abs/1612.06508v1
PDF	http://arxiv.org/pdf/1612.06508v1.pdf
PWC	https://paperswithcode.com/paper/deeply-aggregated-alternating-minimization
Repo
Framework

Pose from Action: Unsupervised Learning of Pose Features based on Motion


Title	Pose from Action: Unsupervised Learning of Pose Features based on Motion
Authors	Senthil Purushwalkam, Abhinav Gupta
Abstract	Human actions are comprised of a sequence of poses. This makes videos of humans a rich and dense source of human poses. We propose an unsupervised method to learn pose features from videos that exploits a signal which is complementary to appearance and can be used as supervision: motion. The key idea is that humans go through poses in a predictable manner while performing actions. Hence, given two poses, it should be possible to model the motion that caused the change between them. We represent each of the poses as a feature in a CNN (Appearance ConvNet) and generate a motion encoding from optical flow maps using a separate CNN (Motion ConvNet). The data for this task is automatically generated allowing us to train without human supervision. We demonstrate the strength of the learned representation by finetuning the trained model for Pose Estimation on the FLIC dataset, for static image action recognition on PASCAL and for action recognition in videos on UCF101 and HMDB51.
Tasks	Action Recognition In Videos, Optical Flow Estimation, Pose Estimation, Temporal Action Localization
Published	2016-09-18
URL	http://arxiv.org/abs/1609.05420v1
PDF	http://arxiv.org/pdf/1609.05420v1.pdf
PWC	https://paperswithcode.com/paper/pose-from-action-unsupervised-learning-of
Repo
Framework

Characterizing the maximum parameter of the total-variation denoising through the pseudo-inverse of the divergence


Title	Characterizing the maximum parameter of the total-variation denoising through the pseudo-inverse of the divergence
Authors	Charles-Alban Deledalle, Nicolas Papadakis, Joseph Salmon, Samuel Vaiter
Abstract	We focus on the maximum regularization parameter for anisotropic total-variation denoising. It corresponds to the minimum value of the regularization parameter above which the solution remains constant. While this value is well know for the Lasso, such a critical value has not been investigated in details for the total-variation. Though, it is of importance when tuning the regularization parameter as it allows fixing an upper-bound on the grid for which the optimal parameter is sought. We establish a closed form expression for the one-dimensional case, as well as an upper-bound for the two-dimensional case, that appears reasonably tight in practice. This problem is directly linked to the computation of the pseudo-inverse of the divergence, which can be quickly obtained by performing convolutions in the Fourier domain.
Tasks	Denoising
Published	2016-12-08
URL	http://arxiv.org/abs/1612.03080v1
PDF	http://arxiv.org/pdf/1612.03080v1.pdf
PWC	https://paperswithcode.com/paper/characterizing-the-maximum-parameter-of-the
Repo
Framework

TensorLog: A Differentiable Deductive Database


Title	TensorLog: A Differentiable Deductive Database
Authors	William W. Cohen
Abstract	Large knowledge bases (KBs) are useful in many tasks, but it is unclear how to integrate this sort of knowledge into “deep” gradient-based learning systems. To address this problem, we describe a probabilistic deductive database, called TensorLog, in which reasoning uses a differentiable process. In TensorLog, each clause in a logical theory is first converted into certain type of factor graph. Then, for each type of query to the factor graph, the message-passing steps required to perform belief propagation (BP) are “unrolled” into a function, which is differentiable. We show that these functions can be composed recursively to perform inference in non-trivial logical theories containing multiple interrelated clauses and predicates. Both compilation and inference in TensorLog are efficient: compilation is linear in theory size and proof depth, and inference is linear in database size and the number of message-passing steps used in BP. We also present experimental results with TensorLog and discuss its relationship to other first-order probabilistic logics.
Tasks
Published	2016-05-20
URL	http://arxiv.org/abs/1605.06523v2
PDF	http://arxiv.org/pdf/1605.06523v2.pdf
PWC	https://paperswithcode.com/paper/tensorlog-a-differentiable-deductive-database
Repo
Framework

Extracting Actionability from Machine Learning Models by Sub-optimal Deterministic Planning


Title	Extracting Actionability from Machine Learning Models by Sub-optimal Deterministic Planning
Authors	Qiang Lyu, Yixin Chen, Zhaorong Li, Zhicheng Cui, Ling Chen, Xing Zhang, Haihua Shen
Abstract	A main focus of machine learning research has been improving the generalization accuracy and efficiency of prediction models. Many models such as SVM, random forest, and deep neural nets have been proposed and achieved great success. However, what emerges as missing in many applications is actionability, i.e., the ability to turn prediction results into actions. For example, in applications such as customer relationship management, clinical prediction, and advertisement, the users need not only accurate prediction, but also actionable instructions which can transfer an input to a desirable goal (e.g., higher profit repays, lower morbidity rates, higher ads hit rates). Existing effort in deriving such actionable knowledge is few and limited to simple action models which restricted to only change one attribute for each action. The dilemma is that in many real applications those action models are often more complex and harder to extract an optimal solution. In this paper, we propose a novel approach that achieves actionability by combining learning with planning, two core areas of AI. In particular, we propose a framework to extract actionable knowledge from random forest, one of the most widely used and best off-the-shelf classifiers. We formulate the actionability problem to a sub-optimal action planning (SOAP) problem, which is to find a plan to alter certain features of a given input so that the random forest would yield a desirable output, while minimizing the total costs of actions. Technically, the SOAP problem is formulated in the SAS+ planning formalism, and solved using a Max-SAT based approach. Our experimental results demonstrate the effectiveness and efficiency of the proposed approach on a personal credit dataset and other benchmarks. Our work represents a new application of automated planning on an emerging and challenging machine learning paradigm.
Tasks
Published	2016-11-03
URL	http://arxiv.org/abs/1611.00873v1
PDF	http://arxiv.org/pdf/1611.00873v1.pdf
PWC	https://paperswithcode.com/paper/extracting-actionability-from-machine
Repo
Framework

Recycling Randomness with Structure for Sublinear time Kernel Expansions


Title	Recycling Randomness with Structure for Sublinear time Kernel Expansions
Authors	Krzysztof Choromanski, Vikas Sindhwani
Abstract	We propose a scheme for recycling Gaussian random vectors into structured matrices to approximate various kernel functions in sublinear time via random embeddings. Our framework includes the Fastfood construction as a special case, but also extends to Circulant, Toeplitz and Hankel matrices, and the broader family of structured matrices that are characterized by the concept of low-displacement rank. We introduce notions of coherence and graph-theoretic structural constants that control the approximation quality, and prove unbiasedness and low-variance properties of random feature maps that arise within our framework. For the case of low-displacement matrices, we show how the degree of structure and randomness can be controlled to reduce statistical variance at the cost of increased computation and storage requirements. Empirical results strongly support our theory and justify the use of a broader family of structured matrices for scaling up kernel methods using random features.
Tasks
Published	2016-05-29
URL	http://arxiv.org/abs/1605.09049v1
PDF	http://arxiv.org/pdf/1605.09049v1.pdf
PWC	https://paperswithcode.com/paper/recycling-randomness-with-structure-for
Repo
Framework

Kernel-based Tests for Joint Independence


Title	Kernel-based Tests for Joint Independence
Authors	Niklas Pfister, Peter Bühlmann, Bernhard Schölkopf, Jonas Peters
Abstract	We investigate the problem of testing whether $d$ random variables, which may or may not be continuous, are jointly (or mutually) independent. Our method builds on ideas of the two variable Hilbert-Schmidt independence criterion (HSIC) but allows for an arbitrary number of variables. We embed the $d$-dimensional joint distribution and the product of the marginals into a reproducing kernel Hilbert space and define the $d$-variable Hilbert-Schmidt independence criterion (dHSIC) as the squared distance between the embeddings. In the population case, the value of dHSIC is zero if and only if the $d$ variables are jointly independent, as long as the kernel is characteristic. Based on an empirical estimate of dHSIC, we define three different non-parametric hypothesis tests: a permutation test, a bootstrap test and a test based on a Gamma approximation. We prove that the permutation test achieves the significance level and that the bootstrap test achieves pointwise asymptotic significance level as well as pointwise asymptotic consistency (i.e., it is able to detect any type of fixed dependence in the large sample limit). The Gamma approximation does not come with these guarantees; however, it is computationally very fast and for small $d$, it performs well in practice. Finally, we apply the test to a problem in causal discovery.
Tasks	Causal Discovery
Published	2016-03-01
URL	http://arxiv.org/abs/1603.00285v3
PDF	http://arxiv.org/pdf/1603.00285v3.pdf
PWC	https://paperswithcode.com/paper/kernel-based-tests-for-joint-independence
Repo
Framework

Extracting Keyword for Disambiguating Name Based on the Overlap Principle


Title	Extracting Keyword for Disambiguating Name Based on the Overlap Principle
Authors	Mahyuddin K. M. Nasution
Abstract	Name disambiguation has become one of the main themes in the Semantic Web agenda. The semantic web is an extension of the current Web in which information is not only given well-defined meaning, but also has many purposes that contain the ambiguous naturally or a lot of thing came with the overlap, mainly deals with the persons name. Therefore, we develop an approach to extract keywords from web snippet with utilizing the overlap principle, a concept to understand things with ambiguous, whereby features of person are generated for dealing with the variety of web, the web is steadily gaining ground in the semantic research.
Tasks
Published	2016-01-30
URL	http://arxiv.org/abs/1602.00104v1
PDF	http://arxiv.org/pdf/1602.00104v1.pdf
PWC	https://paperswithcode.com/paper/extracting-keyword-for-disambiguating-name
Repo
Framework

Here’s My Point: Joint Pointer Architecture for Argument Mining


Title	Here’s My Point: Joint Pointer Architecture for Argument Mining
Authors	Peter Potash, Alexey Romanov, Anna Rumshisky
Abstract	One of the major goals in automated argumentation mining is to uncover the argument structure present in argumentative text. In order to determine this structure, one must understand how different individual components of the overall argument are linked. General consensus in this field dictates that the argument components form a hierarchy of persuasion, which manifests itself in a tree structure. This work provides the first neural network-based approach to argumentation mining, focusing on the two tasks of extracting links between argument components, and classifying types of argument components. In order to solve this problem, we propose to use a joint model that is based on a Pointer Network architecture. A Pointer Network is appealing for this task for the following reasons: 1) It takes into account the sequential nature of argument components; 2) By construction, it enforces certain properties of the tree structure present in argument relations; 3) The hidden representations can be applied to auxiliary tasks. In order to extend the contribution of the original Pointer Network model, we construct a joint model that simultaneously attempts to learn the type of argument component, as well as continuing to predict links between argument components. The proposed joint model achieves state-of-the-art results on two separate evaluation corpora, achieving far superior performance than a regular Pointer Network model. Our results show that optimizing for both tasks, and adding a fully-connected layer prior to recurrent neural network input, is crucial for high performance.
Tasks	Argument Mining
Published	2016-12-28
URL	http://arxiv.org/abs/1612.08994v2
PDF	http://arxiv.org/pdf/1612.08994v2.pdf
PWC	https://paperswithcode.com/paper/heres-my-point-joint-pointer-architecture-for
Repo
Framework

Image Clustering without Ground Truth


Title	Image Clustering without Ground Truth
Authors	Abhisek Dash, Sujoy Chatterjee, Tripti Prasad, Malay Bhattacharyya
Abstract	Cluster analysis has become one of the most exercised research areas over the past few decades in computer science. As a consequence, numerous clustering algorithms have already been developed to find appropriate partitions of a set of objects. Given multiple such clustering solutions, it is a challenging task to obtain an ensemble of these solutions. This becomes more challenging when the ground truth about the number of clusters is unavailable. In this paper, we introduce a crowd-powered model to collect solutions of image clustering from the general crowd and pose it as a clustering ensemble problem with variable number of clusters. The varying number of clusters basically reflects the crowd workers’ perspective toward a particular set of objects. We allow a set of crowd workers to independently cluster the images as per their perceptions. We address the problem by finding out centroid of the clusters using an appropriate distance measure and prioritize the likelihood of similarity of the individual cluster sets. The effectiveness of the proposed method is demonstrated by applying it on multiple artificial datasets obtained from crowd.
Tasks	Image Clustering
Published	2016-10-25
URL	http://arxiv.org/abs/1610.07758v1
PDF	http://arxiv.org/pdf/1610.07758v1.pdf
PWC	https://paperswithcode.com/paper/image-clustering-without-ground-truth
Repo
Framework

Boost K-Means


Title	Boost K-Means
Authors	Wan-Lei Zhao, Cheng-Hao Deng, Chong-Wah Ngo
Abstract	Due to its simplicity and versatility, k-means remains popular since it was proposed three decades ago. The performance of k-means has been enhanced from different perspectives over the years. Unfortunately, a good trade-off between quality and efficiency is hardly reached. In this paper, a novel k-means variant is presented. Different from most of k-means variants, the clustering procedure is driven by an explicit objective function, which is feasible for the whole l2-space. The classic egg-chicken loop in k-means has been simplified to a pure stochastic optimization procedure. The procedure of k-means becomes simpler and converges to a considerably better local optima. The effectiveness of this new variant has been studied extensively in different contexts, such as document clustering, nearest neighbor search and image clustering. Superior performance is observed across different scenarios.
Tasks	Image Clustering, Stochastic Optimization
Published	2016-10-08
URL	http://arxiv.org/abs/1610.02483v2
PDF	http://arxiv.org/pdf/1610.02483v2.pdf
PWC	https://paperswithcode.com/paper/boost-k-means
Repo
Framework

Aggregating Binary Local Descriptors for Image Retrieval


Title	Aggregating Binary Local Descriptors for Image Retrieval
Authors	Giuseppe Amato, Fabrizio Falchi, Lucia Vadicamo
Abstract	Content-Based Image Retrieval based on local features is computationally expensive because of the complexity of both extraction and matching of local feature. On one hand, the cost for extracting, representing, and comparing local visual descriptors has been dramatically reduced by recently proposed binary local features. On the other hand, aggregation techniques provide a meaningful summarization of all the extracted feature of an image into a single descriptor, allowing us to speed up and scale up the image search. Only a few works have recently mixed together these two research directions, defining aggregation methods for binary local features, in order to leverage on the advantage of both approaches. In this paper, we report an extensive comparison among state-of-the-art aggregation methods applied to binary features. Then, we mathematically formalize the application of Fisher Kernels to Bernoulli Mixture Models. Finally, we investigate the combination of the aggregated binary features with the emerging Convolutional Neural Network (CNN) features. Our results show that aggregation methods on binary features are effective and represent a worthwhile alternative to the direct matching. Moreover, the combination of the CNN with the Fisher Vector (FV) built upon binary features allowed us to obtain a relative improvement over the CNN results that is in line with that recently obtained using the combination of the CNN with the FV built upon SIFTs. The advantage of using the FV built upon binary features is that the extraction process of binary features is about two order of magnitude faster than SIFTs.
Tasks	Content-Based Image Retrieval, Image Retrieval
Published	2016-08-02
URL	http://arxiv.org/abs/1608.00813v2
PDF	http://arxiv.org/pdf/1608.00813v2.pdf
PWC	https://paperswithcode.com/paper/aggregating-binary-local-descriptors-for
Repo
Framework