July 29, 2019

2872 words 14 mins read

Paper Group ANR 100

Robust Data Geometric Structure Aligned Close yet Discriminative Domain Adaptation. Emotional Filters: Automatic Image Transformation for Inducing Affect. Unlocking the Potential of Simulators: Design with RL in Mind. Prostate Cancer Diagnosis using Deep Learning with 3D Multiparametric MRI. Variational Joint Filtering. Minimal Solvers for Monocula …

Robust Data Geometric Structure Aligned Close yet Discriminative Domain Adaptation


Title	Robust Data Geometric Structure Aligned Close yet Discriminative Domain Adaptation
Authors	Lingkun Luo, Xiaofang Wang, Shiqiang Hu, Liming Chen
Abstract	Domain adaptation (DA) is transfer learning which aims to leverage labeled data in a related source domain to achieve informed knowledge transfer and help the classification of unlabeled data in a target domain. In this paper, we propose a novel DA method, namely Robust Data Geometric Structure Aligned, Close yet Discriminative Domain Adaptation (RSA-CDDA), which brings closer, in a latent joint subspace, both source and target data distributions, and aligns inherent hidden source and target data geometric structures while performing discriminative DA in repulsing both interclass source and target data. The proposed method performs domain adaptation between source and target in solving a unified model, which incorporates data distribution constraints, in particular via a nonparametric distance, i.e., Maximum Mean Discrepancy (MMD), as well as constraints on inherent hidden data geometric structure segmentation and alignment between source and target, through low rank and sparse representation. RSA-CDDA achieves the search of a joint subspace in solving the proposed unified model through iterative optimization, alternating Rayleigh quotient algorithm and inexact augmented Lagrange multiplier algorithm. Extensive experiments carried out on standard DA benchmarks, i.e., 16 cross-domain image classification tasks, verify the effectiveness of the proposed method, which consistently outperforms the state-of-the-art methods.
Tasks	Domain Adaptation, Image Classification, Transfer Learning
Published	2017-05-24
URL	http://arxiv.org/abs/1705.08620v1
PDF	http://arxiv.org/pdf/1705.08620v1.pdf
PWC	https://paperswithcode.com/paper/robust-data-geometric-structure-aligned-close
Repo
Framework

Emotional Filters: Automatic Image Transformation for Inducing Affect


Title	Emotional Filters: Automatic Image Transformation for Inducing Affect
Authors	Afsheen Rafaqat Ali, Mohsen Ali
Abstract	Current image transformation and recoloring algorithms try to introduce artistic effects in the photographed images, based on user input of target image(s) or selection of pre-designed filters. These manipulations, although intended to enhance the impact of an image on the viewer, do not include the option of image transformation by specifying the affect information. In this paper we present an automatic image-transformation method that transforms the source image such that it can induce an emotional affect on the viewer, as desired by the user. Our proposed novel image emotion transfer algorithm does not require a user-specified target image. The proposed algorithm uses features extracted from top layers of deep convolutional neural network and the user-specified emotion distribution to select multiple target images from an image database for color transformation, such that the resultant image has desired emotional impact. Our method can handle more diverse set of photographs than the previous methods. We conducted a detailed user study showing the effectiveness of our proposed method. A discussion and reasoning of failure cases has also been provided, indicating inherent limitation of color-transfer based methods in the use of emotion assignment.
Tasks
Published	2017-07-25
URL	http://arxiv.org/abs/1707.08148v2
PDF	http://arxiv.org/pdf/1707.08148v2.pdf
PWC	https://paperswithcode.com/paper/emotional-filters-automatic-image
Repo
Framework

Unlocking the Potential of Simulators: Design with RL in Mind


Title	Unlocking the Potential of Simulators: Design with RL in Mind
Authors	Rika Antonova, Silvia Cruciani
Abstract	Using Reinforcement Learning (RL) in simulation to construct policies useful in real life is challenging. This is often attributed to the sequential decision making aspect: inaccuracies in simulation accumulate over multiple steps, hence the simulated trajectories diverge from what would happen in reality. In our work we show the need to consider another important aspect: the mismatch in simulating control. We bring attention to the need for modeling control as well as dynamics, since oversimplifying assumptions about applying actions of RL policies could make the policies fail on real-world systems. We design a simulator for solving a pivoting task (of interest in Robotics) and demonstrate that even a simple simulator designed with RL in mind outperforms high-fidelity simulators when it comes to learning a policy that is to be deployed on a real robotic system. We show that a phenomenon that is hard to model - friction - could be exploited successfully, even when RL is performed using a simulator with a simple dynamics and noise model. Hence, we demonstrate that as long as the main sources of uncertainty are identified, it could be possible to learn policies applicable to real systems even using a simple simulator. RL-compatible simulators could open the possibilities for applying a wide range of RL algorithms in various fields. This is important, since currently data sparsity in fields like healthcare and education frequently forces researchers and engineers to only consider sample-efficient RL approaches. Successful simulator-aided RL could increase flexibility of experimenting with RL algorithms and help applying RL policies to real-world settings in fields where data is scarce. We believe that lessons learned in Robotics could help other fields design RL-compatible simulators, so we summarize our experience and conclude with suggestions.
Tasks	Decision Making
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02501v1
PDF	http://arxiv.org/pdf/1706.02501v1.pdf
PWC	https://paperswithcode.com/paper/unlocking-the-potential-of-simulators-design
Repo
Framework

Prostate Cancer Diagnosis using Deep Learning with 3D Multiparametric MRI


Title	Prostate Cancer Diagnosis using Deep Learning with 3D Multiparametric MRI
Authors	Saifeng Liu, Huaixiu Zheng, Yesu Feng, Wei Li
Abstract	A novel deep learning architecture (XmasNet) based on convolutional neural networks was developed for the classification of prostate cancer lesions, using the 3D multiparametric MRI data provided by the PROSTATEx challenge. End-to-end training was performed for XmasNet, with data augmentation done through 3D rotation and slicing, in order to incorporate the 3D information of the lesion. XmasNet outperformed traditional machine learning models based on engineered features, for both train and test data. For the test data, XmasNet outperformed 69 methods from 33 participating groups and achieved the second highest AUC (0.84) in the PROSTATEx challenge. This study shows the great potential of deep learning for cancer imaging.
Tasks	Data Augmentation
Published	2017-03-12
URL	http://arxiv.org/abs/1703.04078v1
PDF	http://arxiv.org/pdf/1703.04078v1.pdf
PWC	https://paperswithcode.com/paper/prostate-cancer-diagnosis-using-deep-learning
Repo
Framework

Variational Joint Filtering


Title	Variational Joint Filtering
Authors	Yuan Zhao, Il Memming Park
Abstract	New technologies for recording the activity of large neural populations during complex behavior provide exciting opportunities for investigating the neural computations that underlie perception, cognition, and decision-making. Nonlinear state-space models provide an interpretable signal processing framework by combining an intuitive dynamical system with a probabilistic observation model, which can provide insights into neural dynamics, neural computation, and development of neural prosthetics and treatment through feedback control. It yet brings the challenge of learning both latent neural state and the underlying dynamical system because neither is known for neural systems a priori. We developed a flexible online learning framework for latent nonlinear state dynamics and filtered latent states. Using the stochastic gradient variational Bayes approach, our method jointly optimizes the parameters of the nonlinear dynamical system, the observation model, and the black-box recognition model. Unlike previous approaches, our framework can incorporate non-trivial distributions of observation noise and has constant time and space complexity. These features make our approach amenable to real-time applications and the potential to automate analysis and experimental design in ways that testably track and modify behavior using stimuli designed to influence learning.
Tasks	Decision Making, Time Series
Published	2017-07-27
URL	https://arxiv.org/abs/1707.09049v4
PDF	https://arxiv.org/pdf/1707.09049v4.pdf
PWC	https://paperswithcode.com/paper/variational-joint-filtering
Repo
Framework

Minimal Solvers for Monocular Rolling Shutter Compensation under Ackermann Motion


Title	Minimal Solvers for Monocular Rolling Shutter Compensation under Ackermann Motion
Authors	Pulak Purkait, Christopher Zach
Abstract	Modern automotive vehicles are often equipped with a budget commercial rolling shutter camera. These devices often produce distorted images due to the inter-row delay of the camera while capturing the image. Recent methods for monocular rolling shutter motion compensation utilize blur kernel and the straightness property of line segments. However, these methods are limited to handling rotational motion and also are not fast enough to operate in real time. In this paper, we propose a minimal solver for the rolling shutter motion compensation which assumes known vertical direction of the camera. Thanks to the Ackermann motion model of vehicles which consists of only two motion parameters, and two parameters for the simplified depth assumption that lead to a 4-line algorithm. The proposed minimal solver estimates the rolling shutter camera motion efficiently and accurately. The extensive experiments on real and simulated datasets demonstrate the benefits of our approach in terms of qualitative and quantitative results.
Tasks	Motion Compensation
Published	2017-12-08
URL	http://arxiv.org/abs/1712.03159v1
PDF	http://arxiv.org/pdf/1712.03159v1.pdf
PWC	https://paperswithcode.com/paper/minimal-solvers-for-monocular-rolling-shutter
Repo
Framework

Morpheo: Traceable Machine Learning on Hidden data


Title	Morpheo: Traceable Machine Learning on Hidden data
Authors	Mathieu Galtier, Camille Marini
Abstract	Morpheo is a transparent and secure machine learning platform collecting and analysing large datasets. It aims at building state-of-the art prediction models in various fields where data are sensitive. Indeed, it offers strong privacy of data and algorithm, by preventing anyone to read the data, apart from the owner and the chosen algorithms. Computations in Morpheo are orchestrated by a blockchain infrastructure, thus offering total traceability of operations. Morpheo aims at building an attractive economic ecosystem around data prediction by channelling crypto-money from prediction requests to useful data and algorithms providers. Morpheo is designed to handle multiple data sources in a transfer learning approach in order to mutualize knowledge acquired from large datasets for applications with smaller but similar datasets.
Tasks	Transfer Learning
Published	2017-04-17
URL	http://arxiv.org/abs/1704.05017v1
PDF	http://arxiv.org/pdf/1704.05017v1.pdf
PWC	https://paperswithcode.com/paper/morpheo-traceable-machine-learning-on-hidden
Repo
Framework

Multi-Level and Multi-Scale Feature Aggregation Using Sample-level Deep Convolutional Neural Networks for Music Classification


Title	Multi-Level and Multi-Scale Feature Aggregation Using Sample-level Deep Convolutional Neural Networks for Music Classification
Authors	Jongpil Lee, Juhan Nam
Abstract	Music tag words that describe music audio by text have different levels of abstraction. Taking this issue into account, we propose a music classification approach that aggregates multi-level and multi-scale features using pre-trained feature extractors. In particular, the feature extractors are trained in sample-level deep convolutional neural networks using raw waveforms. We show that this approach achieves state-of-the-art results on several music classification datasets.
Tasks	Music Classification
Published	2017-06-21
URL	http://arxiv.org/abs/1706.06810v1
PDF	http://arxiv.org/pdf/1706.06810v1.pdf
PWC	https://paperswithcode.com/paper/multi-level-and-multi-scale-feature-1
Repo
Framework

Premise Selection for Theorem Proving by Deep Graph Embedding


Title	Premise Selection for Theorem Proving by Deep Graph Embedding
Authors	Mingzhe Wang, Yihe Tang, Jian Wang, Jia Deng
Abstract	We propose a deep learning-based approach to the problem of premise selection: selecting mathematical statements relevant for proving a given conjecture. We represent a higher-order logic formula as a graph that is invariant to variable renaming but still fully preserves syntactic and semantic information. We then embed the graph into a vector via a novel embedding method that preserves the information of edge ordering. Our approach achieves state-of-the-art results on the HolStep dataset, improving the classification accuracy from 83% to 90.3%.
Tasks	Automated Theorem Proving, Graph Embedding
Published	2017-09-28
URL	http://arxiv.org/abs/1709.09994v1
PDF	http://arxiv.org/pdf/1709.09994v1.pdf
PWC	https://paperswithcode.com/paper/premise-selection-for-theorem-proving-by-deep
Repo
Framework

Dynamic Reconfiguration of Mission Parameters in Underwater Human-Robot Collaboration


Title	Dynamic Reconfiguration of Mission Parameters in Underwater Human-Robot Collaboration
Authors	Md Jahidul Islam, Marc Ho, Junaed Sattar
Abstract	This paper presents a real-time programming and parameter reconfiguration method for autonomous underwater robots in human-robot collaborative tasks. Using a set of intuitive and meaningful hand gestures, we develop a syntactically simple framework that is computationally more efficient than a complex, grammar-based approach. In the proposed framework, a convolutional neural network is trained to provide accurate hand gesture recognition; subsequently, a finite-state machine-based deterministic model performs efficient gesture-to-instruction mapping, and further improves robustness of the interaction scheme. The key aspect of this framework is that it can be easily adopted by divers for communicating simple instructions to underwater robots without using artificial tags such as fiducial markers, or requiring them to memorize a potentially complex set of language rules. Extensive experiments are performed both on field-trial data and through simulation, which demonstrate the robustness, efficiency, and portability of this framework in a number of different scenarios. Finally, a user interaction study is presented that illustrates the gain in usability of our proposed interaction framework compared to the existing methods for underwater domains.
Tasks	Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition
Published	2017-09-26
URL	http://arxiv.org/abs/1709.08772v8
PDF	http://arxiv.org/pdf/1709.08772v8.pdf
PWC	https://paperswithcode.com/paper/dynamic-reconfiguration-of-mission-parameters
Repo
Framework

Deep Learning for Accelerated Reliability Analysis of Infrastructure Networks


Title	Deep Learning for Accelerated Reliability Analysis of Infrastructure Networks
Authors	Mohammad Amin Nabian, Hadi Meidani
Abstract	Natural disasters can have catastrophic impacts on the functionality of infrastructure systems and cause severe physical and socio-economic losses. Given budget constraints, it is crucial to optimize decisions regarding mitigation, preparedness, response, and recovery practices for these systems. This requires accurate and efficient means to evaluate the infrastructure system reliability. While numerous research efforts have addressed and quantified the impact of natural disasters on infrastructure systems, typically using the Monte Carlo approach, they still suffer from high computational cost and, thus, are of limited applicability to large systems. This paper presents a deep learning framework for accelerating infrastructure system reliability analysis. In particular, two distinct deep neural network surrogates are constructed and studied: (1) A classifier surrogate which speeds up the connectivity determination of networks, and (2) An end-to-end surrogate that replaces a number of components such as roadway status realization, connectivity determination, and connectivity averaging. The proposed approach is applied to a simulation-based study of the two-terminal connectivity of a California transportation network subject to extreme probabilistic earthquake events. Numerical results highlight the effectiveness of the proposed approach in accelerating the transportation system two-terminal reliability analysis with extremely high prediction accuracy.
Tasks
Published	2017-08-28
URL	http://arxiv.org/abs/1708.08551v1
PDF	http://arxiv.org/pdf/1708.08551v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-accelerated-reliability
Repo
Framework

Interpretable Convolutional Neural Networks


Title	Interpretable Convolutional Neural Networks
Authors	Quanshi Zhang, Ying Nian Wu, Song-Chun Zhu
Abstract	This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high conv-layer represents a certain object part. We do not need any annotations of object parts or textures to supervise the learning process. Instead, the interpretable CNN automatically assigns each filter in a high conv-layer with an object part during the learning process. Our method can be applied to different types of CNNs with different structures. The clear knowledge representation in an interpretable CNN can help people understand the logics inside a CNN, i.e., based on which patterns the CNN makes the decision. Experiments showed that filters in an interpretable CNN were more semantically meaningful than those in traditional CNNs.
Tasks
Published	2017-10-02
URL	http://arxiv.org/abs/1710.00935v4
PDF	http://arxiv.org/pdf/1710.00935v4.pdf
PWC	https://paperswithcode.com/paper/interpretable-convolutional-neural-networks-2
Repo
Framework

Motion Feature Augmented Recurrent Neural Network for Skeleton-based Dynamic Hand Gesture Recognition


Title	Motion Feature Augmented Recurrent Neural Network for Skeleton-based Dynamic Hand Gesture Recognition
Authors	Xinghao Chen, Hengkai Guo, Guijin Wang, Li Zhang
Abstract	Dynamic hand gesture recognition has attracted increasing interests because of its importance for human computer interaction. In this paper, we propose a new motion feature augmented recurrent neural network for skeleton-based dynamic hand gesture recognition. Finger motion features are extracted to describe finger movements and global motion features are utilized to represent the global movement of hand skeleton. These motion features are then fed into a bidirectional recurrent neural network (RNN) along with the skeleton sequence, which can augment the motion features for RNN and improve the classification performance. Experiments demonstrate that our proposed method is effective and outperforms start-of-the-art methods.
Tasks	Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition, Skeleton Based Action Recognition
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03278v1
PDF	http://arxiv.org/pdf/1708.03278v1.pdf
PWC	https://paperswithcode.com/paper/motion-feature-augmented-recurrent-neural
Repo
Framework

Probabilistic Relation Induction in Vector Space Embeddings


Title	Probabilistic Relation Induction in Vector Space Embeddings
Authors	Zied Bouraoui, Shoaib Jameel, Steven Schockaert
Abstract	Word embeddings have been found to capture a surprisingly rich amount of syntactic and semantic knowledge. However, it is not yet sufficiently well-understood how the relational knowledge that is implicitly encoded in word embeddings can be extracted in a reliable way. In this paper, we propose two probabilistic models to address this issue. The first model is based on the common relations-as-translations view, but is cast in a probabilistic setting. Our second model is based on the much weaker assumption that there is a linear relationship between the vector representations of related words. Compared to existing approaches, our models lead to more accurate predictions, and they are more explicit about what can and cannot be extracted from the word embedding.
Tasks	Word Embeddings
Published	2017-08-21
URL	http://arxiv.org/abs/1708.06266v1
PDF	http://arxiv.org/pdf/1708.06266v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-relation-induction-in-vector
Repo
Framework

Method for Aspect-Based Sentiment Annotation Using Rhetorical Analysis


Title	Method for Aspect-Based Sentiment Annotation Using Rhetorical Analysis
Authors	Łukasz Augustyniak, Krzysztof Rajda, Tomasz Kajdanowicz
Abstract	This paper fills a gap in aspect-based sentiment analysis and aims to present a new method for preparing and analysing texts concerning opinion and generating user-friendly descriptive reports in natural language. We present a comprehensive set of techniques derived from Rhetorical Structure Theory and sentiment analysis to extract aspects from textual opinions and then build an abstractive summary of a set of opinions. Moreover, we propose aspect-aspect graphs to evaluate the importance of aspects and to filter out unimportant ones from the summary. Additionally, the paper presents a prototype solution of data flow with interesting and valuable results. The proposed method’s results proved the high accuracy of aspect detection when applied to the gold standard dataset.
Tasks	Aspect-Based Sentiment Analysis, Sentiment Analysis
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04491v1
PDF	http://arxiv.org/pdf/1709.04491v1.pdf
PWC	https://paperswithcode.com/paper/method-for-aspect-based-sentiment-annotation
Repo
Framework