October 19, 2019

2936 words 14 mins read

Paper Group ANR 206

Knowledge-enriched Two-layered Attention Network for Sentiment Analysis. Law and Adversarial Machine Learning. ClusterNet: 3D Instance Segmentation in RGB-D Images. Deep Discriminative Learning for Unsupervised Domain Adaptation. Knowledge Graph Embedding with Multiple Relation Projections. Cross-lingual Word Analogies using Linear Transformations …

Knowledge-enriched Two-layered Attention Network for Sentiment Analysis


Title	Knowledge-enriched Two-layered Attention Network for Sentiment Analysis
Authors	Abhishek Kumar, Daisuke Kawahara, Sadao Kurohashi
Abstract	We propose a novel two-layered attention network based on Bidirectional Long Short-Term Memory for sentiment analysis. The novel two-layered attention network takes advantage of the external knowledge bases to improve the sentiment prediction. It uses the Knowledge Graph Embedding generated using the WordNet. We build our model by combining the two-layered attention network with the supervised model based on Support Vector Regression using a Multilayer Perceptron network for sentiment analysis. We evaluate our model on the benchmark dataset of SemEval 2017 Task 5. Experimental results show that the proposed model surpasses the top system of SemEval 2017 Task 5. The model performs significantly better by improving the state-of-the-art system at SemEval 2017 Task 5 by 1.7 and 3.7 points for sub-tracks 1 and 2 respectively.
Tasks	Graph Embedding, Knowledge Graph Embedding, Sentiment Analysis
Published	2018-05-20
URL	http://arxiv.org/abs/1805.07819v4
PDF	http://arxiv.org/pdf/1805.07819v4.pdf
PWC	https://paperswithcode.com/paper/knowledge-enriched-two-layered-attention
Repo
Framework

Law and Adversarial Machine Learning


Title	Law and Adversarial Machine Learning
Authors	Ram Shankar Siva Kumar, David R. O’Brien, Kendra Albert, Salome Vilojen
Abstract	When machine learning systems fail because of adversarial manipulation, how should society expect the law to respond? Through scenarios grounded in adversarial ML literature, we explore how some aspects of computer crime, copyright, and tort law interface with perturbation, poisoning, model stealing and model inversion attacks to show how some attacks are more likely to result in liability than others. We end with a call for action to ML researchers to invest in transparent benchmarks of attacks and defenses; architect ML systems with forensics in mind and finally, think more about adversarial machine learning in the context of civil liberties. The paper is targeted towards ML researchers who have no legal background.
Tasks
Published	2018-10-25
URL	http://arxiv.org/abs/1810.10731v3
PDF	http://arxiv.org/pdf/1810.10731v3.pdf
PWC	https://paperswithcode.com/paper/law-and-adversarial-machine-learning
Repo
Framework

ClusterNet: 3D Instance Segmentation in RGB-D Images


Title	ClusterNet: 3D Instance Segmentation in RGB-D Images
Authors	Lin Shao, Ye Tian, Jeannette Bohg
Abstract	We propose a method for instance-level segmentation that uses RGB-D data as input and provides detailed information about the location, geometry and number of individual objects in the scene. This level of understanding is fundamental for autonomous robots. It enables safe and robust decision-making under the large uncertainty of the real-world. In our model, we propose to use the first and second order moments of the object occupancy function to represent an object instance. We train an hourglass Deep Neural Network (DNN) where each pixel in the output votes for the 3D position of the corresponding object center and for the object’s size and pose. The final instance segmentation is achieved through clustering in the space of moments. The object-centric training loss is defined on the output of the clustering. Our method outperforms the state-of-the-art instance segmentation method on our synthesized dataset. We show that our method generalizes well on real-world data achieving visually better segmentation results.
Tasks	3D Instance Segmentation, Decision Making, Instance Segmentation, Semantic Segmentation
Published	2018-07-24
URL	http://arxiv.org/abs/1807.08894v2
PDF	http://arxiv.org/pdf/1807.08894v2.pdf
PWC	https://paperswithcode.com/paper/clusternet-3d-instance-segmentation-in-rgb-d
Repo
Framework

Deep Discriminative Learning for Unsupervised Domain Adaptation


Title	Deep Discriminative Learning for Unsupervised Domain Adaptation
Authors	Rohith AP, Ambedkar Dukkipati, Gaurav Pandey
Abstract	The primary objective of domain adaptation methods is to transfer knowledge from a source domain to a target domain that has similar but different data distributions. Thus, in order to correctly classify the unlabeled target domain samples, the standard approach is to learn a common representation for both source and target domain, thereby indirectly addressing the problem of learning a classifier in the target domain. However, such an approach does not address the task of classification in the target domain directly. In contrast, we propose an approach that directly addresses the problem of learning a classifier in the unlabeled target domain. In particular, we train a classifier to correctly classify the training samples while simultaneously classifying the samples in the target domain in an unsupervised manner. The corresponding model is referred to as Discriminative Encoding for Domain Adaptation (DEDA). We show that this simple approach for performing unsupervised domain adaptation is indeed quite powerful. Our method achieves state of the art results in unsupervised adaptation tasks on various image classification benchmarks. We also obtained state of the art performance on domain adaptation in Amazon reviews sentiment classification dataset. We perform additional experiments when the source data has less labeled examples and also on zero-shot domain adaptation task where no target domain samples are used for training.
Tasks	Domain Adaptation, Image Classification, Sentiment Analysis, Unsupervised Domain Adaptation
Published	2018-11-17
URL	https://arxiv.org/abs/1811.07134v2
PDF	https://arxiv.org/pdf/1811.07134v2.pdf
PWC	https://paperswithcode.com/paper/deep-discriminative-learning-for-unsupervised
Repo
Framework

Knowledge Graph Embedding with Multiple Relation Projections


Title	Knowledge Graph Embedding with Multiple Relation Projections
Authors	Kien Do, Truyen Tran, Svetha Venkatesh
Abstract	Knowledge graphs contain rich relational structures of the world, and thus complement data-driven machine learning in heterogeneous data. One of the most effective methods in representing knowledge graphs is to embed symbolic relations and entities into continuous spaces, where relations are approximately linear translation between projected images of entities in the relation space. However, state-of-the-art relation projection methods such as TransR, TransD or TransSparse do not model the correlation between relations, and thus are not scalable to complex knowledge graphs with thousands of relations, both in computational demand and in statistical robustness. To this end we introduce TransF, a novel translation-based method which mitigates the burden of relation projection by explicitly modeling the basis subspaces of projection matrices. As a result, TransF is far more light weight than the existing projection methods, and is robust when facing a high number of relations. Experimental results on the canonical link prediction task show that our proposed model outperforms competing rivals by a large margin and achieves state-of-the-art performance. Especially, TransF improves by 9%/5% in the head/tail entity prediction task for N-to-1/1-to-N relations over the best performing translation-based method.
Tasks	Graph Embedding, Knowledge Graph Embedding, Knowledge Graphs, Link Prediction
Published	2018-01-26
URL	http://arxiv.org/abs/1801.08641v1
PDF	http://arxiv.org/pdf/1801.08641v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-graph-embedding-with-multiple
Repo
Framework

Cross-lingual Word Analogies using Linear Transformations between Semantic Spaces


Title	Cross-lingual Word Analogies using Linear Transformations between Semantic Spaces
Authors	Tomáš Brychcín, Stephen Eugene Taylor, Lukáš Svoboda
Abstract	We generalize the word analogy task across languages, to provide a new intrinsic evaluation method for cross-lingual semantic spaces. We experiment with six languages within different language families, including English, German, Spanish, Italian, Czech, and Croatian. State-of-the-art monolingual semantic spaces are transformed into a shared space using dictionaries of word translations. We compare several linear transformations and rank them for experiments with monolingual (no transformation), bilingual (one semantic space is transformed to another), and multilingual (all semantic spaces are transformed onto English space) versions of semantic spaces. We show that tested linear transformations preserve relationships between words (word analogies) and lead to impressive results. We achieve average accuracy of 51.1%, 43.1%, and 38.2% for monolingual, bilingual, and multilingual semantic spaces, respectively.
Tasks
Published	2018-07-11
URL	http://arxiv.org/abs/1807.04175v1
PDF	http://arxiv.org/pdf/1807.04175v1.pdf
PWC	https://paperswithcode.com/paper/cross-lingual-word-analogies-using-linear
Repo
Framework

Average Biased ReLU Based CNN Descriptor for Improved Face Retrieval


Title	Average Biased ReLU Based CNN Descriptor for Improved Face Retrieval
Authors	Shiv Ram Dubey, Soumendu Chakraborty
Abstract	The convolutional neural networks (CNN) like AlexNet, GoogleNet, VGGNet, etc. have been proven as the very discriminative feature descriptor for many computer vision problems. The trained CNN model over one dataset performs reasonably well over another dataset of similar type and outperforms the hand-designed feature descriptor. The Rectified Linear Unit (ReLU) layer discards some information in order to introduce the non-linearity. In this paper, it is proposed that the discriminative ability of deep image representation using trained model can be improved by Average Biased ReLU (AB-ReLU) at last few layers. Basically, AB-ReLU improves the discriminative ability by two ways: 1) it also exploits some of the discriminative and discarded negative information of ReLU and 2) it kills the irrelevant and positive information used by ReLU. The VGGFace model already trained in MatConvNet over the VGG-Face dataset is used as the feature descriptor for face retrieval over other face datasets. The proposed approach is tested over six challenging unconstrained and robust face datasets like PubFig, LFW, PaSC, AR, etc. in retrieval framework. It is observed that AB-ReLU is consistently performed better than ReLU using VGGFace pretrained model over face datasets.
Tasks
Published	2018-04-02
URL	http://arxiv.org/abs/1804.02051v1
PDF	http://arxiv.org/pdf/1804.02051v1.pdf
PWC	https://paperswithcode.com/paper/average-biased-relu-based-cnn-descriptor-for
Repo
Framework

Wasserstein Variational Inference


Title	Wasserstein Variational Inference
Authors	Luca Ambrogioni, Umut Güçlü, Yağmur Güçlütürk, Max Hinne, Eric Maris, Marcel A. J. van Gerven
Abstract	This paper introduces Wasserstein variational inference, a new form of approximate Bayesian inference based on optimal transport theory. Wasserstein variational inference uses a new family of divergences that includes both f-divergences and the Wasserstein distance as special cases. The gradients of the Wasserstein variational loss are obtained by backpropagating through the Sinkhorn iterations. This technique results in a very stable likelihood-free training method that can be used with implicit distributions and probabilistic programs. Using the Wasserstein variational inference framework, we introduce several new forms of autoencoders and test their robustness and performance against existing variational autoencoding techniques.
Tasks	Bayesian Inference
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11284v2
PDF	http://arxiv.org/pdf/1805.11284v2.pdf
PWC	https://paperswithcode.com/paper/wasserstein-variational-inference
Repo
Framework

EventNet: Asynchronous Recursive Event Processing


Title	EventNet: Asynchronous Recursive Event Processing
Authors	Yusuke Sekikawa, Kosuke Hara, Hideo Saito
Abstract	Event cameras are bio-inspired vision sensors that mimic retinas to asynchronously report per-pixel intensity changes rather than outputting an actual intensity image at regular intervals. This new paradigm of image sensor offers significant potential advantages; namely, sparse and non-redundant data representation. Unfortunately, however, most of the existing artificial neural network architectures, such as a CNN, require dense synchronous input data, and therefore, cannot make use of the sparseness of the data. We propose EventNet, a neural network designed for real-time processing of asynchronous event streams in a recursive and event-wise manner. EventNet models dependence of the output on tens of thousands of causal events recursively using a novel temporal coding scheme. As a result, at inference time, our network operates in an event-wise manner that is realized with very few sum-of-the-product operations—look-up table and temporal feature aggregation—which enables processing of 1 mega or more events per second on standard CPU. In experiments using real data, we demonstrated the real-time performance and robustness of our framework.
Tasks
Published	2018-12-07
URL	http://arxiv.org/abs/1812.07045v2
PDF	http://arxiv.org/pdf/1812.07045v2.pdf
PWC	https://paperswithcode.com/paper/eventnet-asynchronous-recursive-event
Repo
Framework

Let CONAN tell you a story: Procedural quest generation


Title	Let CONAN tell you a story: Procedural quest generation
Authors	Vincent Breault, Sebastien Ouellet, Jim Davies
Abstract	This work proposes an engine for the Creation Of Novel Adventure Narrative (CONAN), which is a procedural quest generator. It uses a planning approach to story generation. The engine is tested on its ability to create quests, which are sets of actions that must be performed in order to achieve a certain goal, usually for a reward. The engine takes in a world description represented as a set of facts, including characters, locations, and items, and generates quests according to the state of the world and the preferences of the characters. We evaluate quests through the classification of the motivations behind the quests, based on the sequences of actions required to complete the quests. We also compare different world descriptions and analyze the difference in motivations for the quests produced by the engine. Compared against human structural quest analysis, the current engine was found to be able to replicate the quest structures found in commercial video game quests.
Tasks
Published	2018-08-19
URL	http://arxiv.org/abs/1808.06217v1
PDF	http://arxiv.org/pdf/1808.06217v1.pdf
PWC	https://paperswithcode.com/paper/let-conan-tell-you-a-story-procedural-quest
Repo
Framework

Effectiveness of Hierarchical Softmax in Large Scale Classification Tasks


Title	Effectiveness of Hierarchical Softmax in Large Scale Classification Tasks
Authors	Abdul Arfat Mohammed, Venkatesh Umaashankar
Abstract	Typically, Softmax is used in the final layer of a neural network to get a probability distribution for output classes. But the main problem with Softmax is that it is computationally expensive for large scale data sets with large number of possible outputs. To approximate class probability efficiently on such large scale data sets we can use Hierarchical Softmax. LSHTC datasets were used to study the performance of the Hierarchical Softmax. LSHTC datasets have large number of categories. In this paper we evaluate and report the performance of normal Softmax Vs Hierarchical Softmax on LSHTC datasets. This evaluation used macro f1 score as a performance measure. The observation was that the performance of Hierarchical Softmax degrades as the number of classes increase.
Tasks
Published	2018-12-13
URL	http://arxiv.org/abs/1812.05737v1
PDF	http://arxiv.org/pdf/1812.05737v1.pdf
PWC	https://paperswithcode.com/paper/effectiveness-of-hierarchical-softmax-in
Repo
Framework

The Trajectory of Voice Onset Time with Vocal Aging


Title	The Trajectory of Voice Onset Time with Vocal Aging
Authors	Xuanda Chen, Ziyu Xiong, Jian Hu
Abstract	Vocal aging, a universal process of human aging, can largely affect one’s language use, possibly including some subtle acoustic features of one’s utterances like Voice Onset Time. To figure out the time effects, Queen Elizabeth’s Christmas speeches are documented and analyzed in the long-term trend. We build statistical models of time dependence in Voice Onset Time, controlling a wide range of other fixed factors, to present annual variations and the simulated trajectory. It is revealed that the variation range of Voice Onset Time has been narrowing over fifty years with a slight reduction in the mean value, which, possibly, is an effect of diminishing exertion, resulting from subdued muscle contraction, transcending other non-linguistic factors in forming Voice Onset Time patterns over a long time.
Tasks
Published	2018-10-15
URL	http://arxiv.org/abs/1810.07030v1
PDF	http://arxiv.org/pdf/1810.07030v1.pdf
PWC	https://paperswithcode.com/paper/the-trajectory-of-voice-onset-time-with-vocal
Repo
Framework

An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing


Title	An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing
Authors	Xiaolong Ma, Yipeng Zhang, Geng Yuan, Ao Ren, Zhe Li, Jie Han, Jingtong Hu, Yanzhi Wang
Abstract	With recent trend of wearable devices and Internet of Things (IoTs), it becomes attractive to develop hardware-based deep convolutional neural networks (DCNNs) for embedded applications, which require low power/energy consumptions and small hardware footprints. Recent works demonstrated that the Stochastic Computing (SC) technique can radically simplify the hardware implementation of arithmetic units and has the potential to satisfy the stringent power requirements in embedded devices. However, in these works, the memory design optimization is neglected for weight storage, which will inevitably result in large hardware cost. Moreover, if conventional volatile SRAM or DRAM cells are utilized for weight storage, the weights need to be re-initialized whenever the DCNN platform is re-started. In order to overcome these limitations, in this work we adopt an emerging non-volatile Domain-Wall Memory (DWM), which can achieve ultra-high density, to replace SRAM for weight storage in SC-based DCNNs. We propose DW-CNN, the first comprehensive design optimization framework of DWM-based weight storage method. We derive the optimal memory type, precision, and organization, as well as whether to store binary or stochastic numbers. We present effective resource sharing scheme for DWM-based weight storage in the convolutional and fully-connected layers of SC-based DCNNs to achieve a desirable balance among area, power (energy) consumption, and application-level accuracy.
Tasks
Published	2018-02-03
URL	http://arxiv.org/abs/1802.01016v1
PDF	http://arxiv.org/pdf/1802.01016v1.pdf
PWC	https://paperswithcode.com/paper/an-area-and-energy-efficient-design-of-domain
Repo
Framework

Siamese Survival Analysis with Competing Risks


Title	Siamese Survival Analysis with Competing Risks
Authors	Anton Nemchenko, Trent Kyono, Mihaela Van Der Schaar
Abstract	Survival analysis in the presence of multiple possible adverse events, i.e., competing risks, is a pervasive problem in many industries (healthcare, finance, etc.). Since only one event is typically observed, the incidence of an event of interest is often obscured by other related competing events. This nonidentifiability, or inability to estimate true cause-specific survival curves from empirical data, further complicates competing risk survival analysis. We introduce Siamese Survival Prognosis Network (SSPN), a novel deep learning architecture for estimating personalized risk scores in the presence of competing risks. SSPN circumvents the nonidentifiability problem by avoiding the estimation of cause-specific survival curves and instead determines pairwise concordant time-dependent risks, where longer event times are assigned lower risks. Furthermore, SSPN is able to directly optimize an approximation to the C-discrimination index, rather than relying on well-known metrics which are unable to capture the unique requirements of survival analysis with competing risks.
Tasks	Survival Analysis
Published	2018-07-16
URL	http://arxiv.org/abs/1807.05935v2
PDF	http://arxiv.org/pdf/1807.05935v2.pdf
PWC	https://paperswithcode.com/paper/siamese-survival-analysis-with-competing
Repo
Framework

Depth Information Guided Crowd Counting for Complex Crowd Scenes


Title	Depth Information Guided Crowd Counting for Complex Crowd Scenes
Authors	Mingliang Xu, Zhaoyang Ge, Xiaoheng Jiang, Gaoge Cui, Pei Lv, Bing Zhou, Changsheng Xu
Abstract	It is important to monitor and analyze crowd events for the sake of city safety. In an EDOF (extended depth of field) image with a crowded scene, the distribution of people is highly imbalanced. People far away from the camera look much smaller and often occlude each other heavily, while people close to the camera look larger. In such a case, it is difficult to accurately estimate the number of people by using one technique. In this paper, we propose a Depth Information Guided Crowd Counting (DigCrowd) method to deal with crowded EDOF scenes. DigCrowd first uses the depth information of an image to segment the scene into a far-view region and a near-view region. Then Digcrowd maps the far-view region to its crowd density map and uses a detection method to count the people in the near-view region. In addition, we introduce a new crowd dataset that contains 1000 images. Experimental results demonstrate the effectiveness of our DigCrowd method
Tasks	Crowd Counting
Published	2018-03-03
URL	http://arxiv.org/abs/1803.02256v2
PDF	http://arxiv.org/pdf/1803.02256v2.pdf
PWC	https://paperswithcode.com/paper/depth-information-guided-crowd-counting-for
Repo
Framework