October 19, 2019

3151 words 15 mins read

Paper Group ANR 345

An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images. Decoupled Learning for Factorial Marked Temporal Point Processes. Traversing the Continuous Spectrum of Image Retrieval with Deep Dynamic Models. Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode d …

An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images


Title	An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images
Authors	Shuai Chen, Marleen de Bruijne
Abstract	Fully-connected Conditional Random Field (CRF) is often used as post-processing to refine voxel classification results by encouraging spatial coherence. In this paper, we propose a new end-to-end training method called Posterior-CRF. In contrast with previous approaches which use the original image intensity in the CRF, our approach applies 3D, fully connected CRF to the posterior probabilities from a CNN and optimizes both CNN and CRF together. The experiments on white matter hyperintensities segmentation demonstrate that our method outperforms CNN, post-processing CRF and different end-to-end training CRF approaches.
Tasks	Semantic Segmentation
Published	2018-11-08
URL	http://arxiv.org/abs/1811.03549v1
PDF	http://arxiv.org/pdf/1811.03549v1.pdf
PWC	https://paperswithcode.com/paper/an-end-to-end-approach-to-semantic
Repo
Framework

Decoupled Learning for Factorial Marked Temporal Point Processes


Title	Decoupled Learning for Factorial Marked Temporal Point Processes
Authors	Weichang Wu, Junchi Yan, Xiaokang Yang, Hongyuan Zha
Abstract	This paper introduces the factorial marked temporal point process model and presents efficient learning methods. In conventional (multi-dimensional) marked temporal point process models, event is often encoded by a single discrete variable i.e. a marker. In this paper, we describe the factorial marked point processes whereby time-stamped event is factored into multiple markers. Accordingly the size of the infectivity matrix modeling the effect between pairwise markers is in power order w.r.t. the number of the discrete marker space. We propose a decoupled learning method with two learning procedures: i) directly solving the model based on two techniques: Alternating Direction Method of Multipliers and Fast Iterative Shrinkage-Thresholding Algorithm; ii) involving a reformulation that transforms the original problem into a Logistic Regression model for more efficient learning. Moreover, a sparse group regularizer is added to identify the key profile features and event labels. Empirical results on real world datasets demonstrate the efficiency of our decoupled and reformulated method. The source code is available online.
Tasks	Point Processes
Published	2018-01-21
URL	http://arxiv.org/abs/1801.06805v1
PDF	http://arxiv.org/pdf/1801.06805v1.pdf
PWC	https://paperswithcode.com/paper/decoupled-learning-for-factorial-marked
Repo
Framework

Traversing the Continuous Spectrum of Image Retrieval with Deep Dynamic Models


Title	Traversing the Continuous Spectrum of Image Retrieval with Deep Dynamic Models
Authors	Ziad Al-Halah, Andreas M. Lehrmann, Leonid Sigal
Abstract	We introduce the first work to tackle the image retrieval problem as a continuous operation. While the proposed approaches in the literature can be roughly categorized into two main groups: category- and instance-based retrieval, in this work we show that the retrieval task is much richer and more complex. Image similarity goes beyond this discrete vantage point and spans a continuous spectrum among the classical operating points of category and instance similarity. However, current retrieval models are static and incapable of exploring this rich structure of the retrieval space since they are trained and evaluated with a single operating point as a target objective. Hence, we introduce a novel retrieval model that for a given query is capable of producing a dynamic embedding that can target an arbitrary point along the continuous retrieval spectrum. Our model disentangles the visual signal of a query image into its basic components of categorical and attribute information. Furthermore, using a continuous control parameter our model learns to reconstruct a dynamic embedding of the query by mixing these components with different proportions to target a specific point along the retrieval simplex. We demonstrate our idea in a comprehensive evaluation of the proposed model and highlight the advantages of our approach against a set of well-established discrete retrieval models.
Tasks	Continuous Control, Image Retrieval
Published	2018-12-01
URL	http://arxiv.org/abs/1812.00202v2
PDF	http://arxiv.org/pdf/1812.00202v2.pdf
PWC	https://paperswithcode.com/paper/towards-traversing-the-continuous-spectrum-of
Repo
Framework

Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition


Title	Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition
Authors	Ümit Çavuş Büyükşahin, Şeyda Ertekin
Abstract	Many applications in different domains produce large amount of time series data. Making accurate forecasting is critical for many decision makers. Various time series forecasting methods exist which use linear and nonlinear models separately or combination of both. Studies show that combining of linear and nonlinear models can be effective to improve forecasting performance. However, some assumptions that those existing methods make, might restrict their performance in certain situations. We provide a new Autoregressive Integrated Moving Average (ARIMA)-Artificial Neural Network(ANN) hybrid method that work in a more general framework. Experimental results show that strategies for decomposing the original data and for combining linear and nonlinear models throughout the hybridization process are key factors in the forecasting performance of the methods. By using appropriate strategies, our hybrid method can be an effective way to improve forecasting accuracy obtained by traditional hybrid methods and also either of the individual methods used separately.
Tasks	Time Series, Time Series Forecasting
Published	2018-12-30
URL	http://arxiv.org/abs/1812.11526v1
PDF	http://arxiv.org/pdf/1812.11526v1.pdf
PWC	https://paperswithcode.com/paper/improving-forecasting-accuracy-of-time-series
Repo
Framework

Unsupervised Hypergraph Feature Selection via a Novel Point-Weighting Framework and Low-Rank Representation


Title	Unsupervised Hypergraph Feature Selection via a Novel Point-Weighting Framework and Low-Rank Representation
Authors	Ammar Gilani, Maryam Amirmazlaghani
Abstract	Feature selection methods are widely used in order to solve the ‘curse of dimensionality’ problem. Many proposed feature selection frameworks, treat all data points equally; neglecting their different representation power and importance. In this paper, we propose an unsupervised hypergraph feature selection method via a novel point-weighting framework and low-rank representation that captures the importance of different data points. We introduce a novel soft hypergraph with low complexity to model data. Then, we formulate the feature selection as an optimization problem to preserve local relationships and also global structure of data. Our approach for global structure preservation helps the framework overcome the problem of unavailability of data labels in unsupervised learning. The proposed feature selection method treats with different data points based on their importance in defining data structure and representation power. Moreover, since the robustness of feature selection methods against noise and outlier is of great importance, we adopt low-rank representation in our model. Also, we provide an efficient algorithm to solve the proposed optimization problem. The computational cost of the proposed algorithm is lower than many state-of-the-art methods which is of high importance in feature selection tasks. We conducted comprehensive experiments with various evaluation methods on different benchmark data sets. These experiments indicate significant improvement, compared with state-of-the-art feature selection methods.
Tasks	Feature Selection
Published	2018-08-25
URL	http://arxiv.org/abs/1808.08414v2
PDF	http://arxiv.org/pdf/1808.08414v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-hypergraph-feature-selection-via
Repo
Framework

Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection


Title	Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection
Authors	Jing Qian, Mai ElSherief, Elizabeth M. Belding, William Yang Wang
Abstract	Hate speech detection is a critical, yet challenging problem in Natural Language Processing (NLP). Despite the existence of numerous studies dedicated to the development of NLP hate speech detection approaches, the accuracy is still poor. The central problem is that social media posts are short and noisy, and most existing hate speech detection solutions take each post as an isolated input instance, which is likely to yield high false positive and negative rates. In this paper, we radically improve automated hate speech detection by presenting a novel model that leverages intra-user and inter-user representation learning for robust hate speech detection on Twitter. In addition to the target Tweet, we collect and analyze the user’s historical posts to model intra-user Tweet representations. To suppress the noise in a single Tweet, we also model the similar Tweets posted by all other users with reinforced inter-user representation learning techniques. Experimentally, we show that leveraging these two representations can significantly improve the f-score of a strong bidirectional LSTM baseline model by 10.1%.
Tasks	Hate Speech Detection, Representation Learning
Published	2018-04-09
URL	http://arxiv.org/abs/1804.03124v2
PDF	http://arxiv.org/pdf/1804.03124v2.pdf
PWC	https://paperswithcode.com/paper/leveraging-intra-user-and-inter-user
Repo
Framework

Managing App Install Ad Campaigns in RTB: A Q-Learning Approach


Title	Managing App Install Ad Campaigns in RTB: A Q-Learning Approach
Authors	Anit Kumar Sahu, Shaunak Mishra, Narayan Bhamidipati
Abstract	Real time bidding (RTB) enables demand side platforms (bidders) to scale ad campaigns across multiple publishers affiliated to an RTB ad exchange. While driving multiple campaigns for mobile app install ads via RTB, the bidder typically has to: (i) maintain each campaign’s efficiency (i.e., meet advertiser’s target cost-per-install), (ii) be sensitive to advertiser’s budget, and (iii) make profit after payouts to the ad exchange. In this process, there is a sense of delayed rewards for the bidder’s actions; the exchange charges the bidder right after the ad is shown, but the bidder gets to know about resultant installs after considerable delay. This makes it challenging for the bidder to decide beforehand the bid (and corresponding cost charged to advertiser) for each ad display opportunity. To jointly handle the objectives mentioned above, we propose a state space based policy which decides the exchange bid and advertiser cost for each opportunity. The state space captures the current efficiency, budget utilization and profit. The policy based on this state space is trained on past decisions and outcomes via a novel Q-learning algorithm which accounts for the delay in install notifications. In our experiments based on data from app install campaigns managed by Yahoo’s Gemini advertising platform, the Q-learning based policy led to a significant increase in the profit and number of efficient campaigns.
Tasks	Q-Learning
Published	2018-11-11
URL	http://arxiv.org/abs/1811.04475v1
PDF	http://arxiv.org/pdf/1811.04475v1.pdf
PWC	https://paperswithcode.com/paper/managing-app-install-ad-campaigns-in-rtb-a-q
Repo
Framework

Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB


Title	Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB
Authors	Tomoyuki Suzuki, Hirokatsu Kataoka, Yoshimitsu Aoki, Yutaka Satoh
Abstract	In this paper, we propose a novel approach for traffic accident anticipation through (i) Adaptive Loss for Early Anticipation (AdaLEA) and (ii) a large-scale self-annotated incident database for anticipation. The proposed AdaLEA allows a model to gradually learn an earlier anticipation as training progresses. The loss function adaptively assigns penalty weights depending on how early the model can an- ticipate a traffic accident at each epoch. Additionally, we construct a Near-miss Incident DataBase for anticipation. This database contains an enormous number of traffic near- miss incident videos and annotations for detail evaluation of two tasks, risk anticipation and risk-factor anticipation. In our experimental results, we found our proposal achieved the highest scores for risk anticipation (+6.6% better on mean average precision (mAP) and 2.36 sec earlier than previous work on the average time-to-collision (ATTC)) and risk-factor anticipation (+4.3% better on mAP and 0.70 sec earlier than previous work on ATTC).
Tasks
Published	2018-04-08
URL	http://arxiv.org/abs/1804.02675v1
PDF	http://arxiv.org/pdf/1804.02675v1.pdf
PWC	https://paperswithcode.com/paper/anticipating-traffic-accidents-with-adaptive
Repo
Framework

A Survey Of Methods For Explaining Black Box Models


Title	A Survey Of Methods For Explaining Black Box Models
Authors	Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Dino Pedreschi, Fosca Giannotti
Abstract	In the last years many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness sometimes at the cost of scarifying accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, delineating explicitly or implicitly its own definition of interpretability and explanation. The aim of this paper is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. Given a problem definition, a black box type, and a desired explanation this survey should help the researcher to find the proposals more useful for his own work. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective.
Tasks
Published	2018-02-06
URL	http://arxiv.org/abs/1802.01933v3
PDF	http://arxiv.org/pdf/1802.01933v3.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-methods-for-explaining-black-box
Repo
Framework

GraphIE: A Graph-Based Framework for Information Extraction


Title	GraphIE: A Graph-Based Framework for Information Extraction
Authors	Yujie Qian, Enrico Santus, Zhijing Jin, Jiang Guo, Regina Barzilay
Abstract	Most modern Information Extraction (IE) systems are implemented as sequential taggers and only model local dependencies. Non-local and non-sequential context is, however, a valuable source of information to improve predictions. In this paper, we introduce GraphIE, a framework that operates over a graph representing a broad set of dependencies between textual units (i.e. words or sentences). The algorithm propagates information between connected nodes through graph convolutions, generating a richer representation that can be exploited to improve word-level predictions. Evaluation on three different tasks — namely textual, social media and visual information extraction — shows that GraphIE consistently outperforms the state-of-the-art sequence tagging model by a significant margin.
Tasks
Published	2018-10-31
URL	http://arxiv.org/abs/1810.13083v3
PDF	http://arxiv.org/pdf/1810.13083v3.pdf
PWC	https://paperswithcode.com/paper/graphie-a-graph-based-framework-for
Repo
Framework

A Better Resource Allocation Algorithm with Semi-Bandit Feedback


Title	A Better Resource Allocation Algorithm with Semi-Bandit Feedback
Authors	Yuval Dagan, Koby Crammer
Abstract	We study a sequential resource allocation problem between a fixed number of arms. On each iteration the algorithm distributes a resource among the arms in order to maximize the expected success rate. Allocating more of the resource to a given arm increases the probability that it succeeds, yet with a cut-off. We follow Lattimore et al. (2014) and assume that the probability increases linearly until it equals one, after which allocating more of the resource is wasteful. These cut-off values are fixed and unknown to the learner. We present an algorithm for this problem and prove a regret upper bound of $O(\log n)$ improving over the best known bound of $O(\log^2 n)$. Lower bounds we prove show that our upper bound is tight. Simulations demonstrate the superiority of our algorithm.
Tasks
Published	2018-03-28
URL	http://arxiv.org/abs/1803.10415v1
PDF	http://arxiv.org/pdf/1803.10415v1.pdf
PWC	https://paperswithcode.com/paper/a-better-resource-allocation-algorithm-with
Repo
Framework

GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping


Title	GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping
Authors	Erhan Gundogdu, Victor Constantin, Amrollah Seifoddini, Minh Dang, Mathieu Salzmann, Pascal Fua
Abstract	While Physics-Based Simulation (PBS) can accurately drape a 3D garment on a 3D body, it remains too costly for real-time applications, such as virtual try-on. By contrast, inference in a deep network, requiring a single forward pass, is much faster. Taking advantage of this, we propose a novel architecture to fit a 3D garment template to a 3D body. Specifically, we build upon the recent progress in 3D point cloud processing with deep networks to extract garment features at varying levels of detail, including point-wise, patch-wise and global features. We fuse these features with those extracted in parallel from the 3D body, so as to model the cloth-body interactions. The resulting two-stream architecture, which we call as GarNet, is trained using a loss function inspired by physics-based modeling, and delivers visually plausible garment shapes whose 3D points are, on average, less than 1 cm away from those of a PBS method, while running 100 times faster. Moreover, the proposed method can model various garment types with different cutting patterns when parameters of those patterns are given as input to the network.
Tasks
Published	2018-11-27
URL	https://arxiv.org/abs/1811.10983v3
PDF	https://arxiv.org/pdf/1811.10983v3.pdf
PWC	https://paperswithcode.com/paper/garnet-a-two-stream-network-for-fast-and
Repo
Framework


Title	Attribute-Guided Network for Cross-Modal Zero-Shot Hashing
Authors	Zhong Ji, Yuxin Sun, Yunlong Yu, Yanwei Pang, Jungong Han
Abstract	Zero-Shot Hashing aims at learning a hashing model that is trained only by instances from seen categories but can generate well to those of unseen categories. Typically, it is achieved by utilizing a semantic embedding space to transfer knowledge from seen domain to unseen domain. Existing efforts mainly focus on single-modal retrieval task, especially Image-Based Image Retrieval (IBIR). However, as a highlighted research topic in the field of hashing, cross-modal retrieval is more common in real world applications. To address the Cross-Modal Zero-Shot Hashing (CMZSH) retrieval task, we propose a novel Attribute-Guided Network (AgNet), which can perform not only IBIR, but also Text-Based Image Retrieval (TBIR). In particular, AgNet aligns different modal data into a semantically rich attribute space, which bridges the gap caused by modality heterogeneity and zero-shot setting. We also design an effective strategy that exploits the attribute to guide the generation of hash codes for image and text within the same network. Extensive experimental results on three benchmark datasets (AwA, SUN, and ImageNet) demonstrate the superiority of AgNet on both cross-modal and single-modal zero-shot image retrieval tasks.
Tasks	Cross-Modal Retrieval, Image Retrieval
Published	2018-02-06
URL	http://arxiv.org/abs/1802.01943v1
PDF	http://arxiv.org/pdf/1802.01943v1.pdf
PWC	https://paperswithcode.com/paper/attribute-guided-network-for-cross-modal-zero
Repo
Framework

Hierarchical Aggregation Approach for Distributed clustering of spatial datasets


Title	Hierarchical Aggregation Approach for Distributed clustering of spatial datasets
Authors	Malika Bendechache, Nhien-An Le-Khac, M-Tahar Kechadi
Abstract	In this paper, we present a new approach of distributed clustering for spatial datasets, based on an innovative and efficient aggregation technique. This distributed approach consists of two phases: 1) local clustering phase, where each node performs a clustering on its local data, 2) aggregation phase, where the local clusters are aggregated to produce global clusters. This approach is characterised by the fact that the local clusters are represented in a simple and efficient way. And The aggregation phase is designed in such a way that the final clusters are compact and accurate while the overall process is efficient in both response time and memory allocation. We evaluated the approach with different datasets and compared it to well-known clustering techniques. The experimental results show that our approach is very promising and outperforms all those algorithms
Tasks
Published	2018-02-01
URL	http://arxiv.org/abs/1802.00688v1
PDF	http://arxiv.org/pdf/1802.00688v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-aggregation-approach-for
Repo
Framework

Intra-class Variation Isolation in Conditional GANs


Title	Intra-class Variation Isolation in Conditional GANs
Authors	Richard T. Marriott, Sami Romdhani, Liming Chen
Abstract	Current state-of-the-art conditional generative adversarial networks (C-GANs) require strong supervision via labeled datasets in order to generate images with continuously adjustable, disentangled semantics. In this paper we introduce a new formulation of the C-GAN that is able to learn realistic models with continuous, semantically meaningful input parameters and which has the advantage of requiring only the weak supervision of binary attribute labels. We coin the method intra-class variation isolation (IVI) and the resulting network the IVI-GAN. The method allows continuous control over the attributes in synthesised images where precise labels are not readily available. For example, given only labels found using a simple classifier of ambient / non-ambient lighting in images, IVI has enabled us to learn a generative face-image model with controllable lighting that is disentangled from other factors in the synthesised images, such as the identity. We evaluate IVI-GAN on the CelebA and CelebA-HQ datasets, learning to disentangle attributes such as lighting, pose, expression and age, and provide a quantitative comparison of IVI-GAN with a classical continuous C-GAN.
Tasks	Continuous Control
Published	2018-11-27
URL	http://arxiv.org/abs/1811.11296v1
PDF	http://arxiv.org/pdf/1811.11296v1.pdf
PWC	https://paperswithcode.com/paper/intra-class-variation-isolation-in
Repo
Framework