October 19, 2019

2818 words 14 mins read

Paper Group ANR 153

Domain Specific Approximation for Object Detection. Dictionary-Guided Editing Networks for Paraphrase Generation. On Batch Orthogonalization Layers. Dynamic Multi-Level Multi-Task Learning for Sentence Simplification. A Distributed Extension of the Turing Machine. Finite Time Adaptive Stabilization of LQ Systems. Tool Breakage Detection using Deep …

Domain Specific Approximation for Object Detection


Title	Domain Specific Approximation for Object Detection
Authors	Ting-Wu Chin, Chia-Lin Yu, Matthew Halpern, Hasan Genc, Shiao-Li Tsao, Vijay Janapa Reddi
Abstract	There is growing interest in object detection in advanced driver assistance systems and autonomous robots and vehicles. To enable such innovative systems, we need faster object detection. In this work, we investigate the trade-off between accuracy and speed with domain-specific approximations, i.e. category-aware image size scaling and proposals scaling, for two state-of-the-art deep learning-based object detection meta-architectures. We study the effectiveness of applying approximation both statically and dynamically to understand the potential and the applicability of them. By conducting experiments on the ImageNet VID dataset, we show that domain-specific approximation has great potential to improve the speed of the system without deteriorating the accuracy of object detectors, i.e. up to 7.5x speedup for dynamic domain-specific approximation. To this end, we present our insights toward harvesting domain-specific approximation as well as devise a proof-of-concept runtime, AutoFocus, that exploits dynamic domain-specific approximation.
Tasks	Object Detection
Published	2018-10-04
URL	http://arxiv.org/abs/1810.02010v1
PDF	http://arxiv.org/pdf/1810.02010v1.pdf
PWC	https://paperswithcode.com/paper/domain-specific-approximation-for-object
Repo
Framework

Dictionary-Guided Editing Networks for Paraphrase Generation


Title	Dictionary-Guided Editing Networks for Paraphrase Generation
Authors	Shaohan Huang, Yu Wu, Furu Wei, Ming Zhou
Abstract	An intuitive way for a human to write paraphrase sentences is to replace words or phrases in the original sentence with their corresponding synonyms and make necessary changes to ensure the new sentences are fluent and grammatically correct. We propose a novel approach to modeling the process with dictionary-guided editing networks which effectively conduct rewriting on the source sentence to generate paraphrase sentences. It jointly learns the selection of the appropriate word level and phrase level paraphrase pairs in the context of the original sentence from an off-the-shelf dictionary as well as the generation of fluent natural language sentences. Specifically, the system retrieves a set of word level and phrase level araphrased pairs derived from the Paraphrase Database (PPDB) for the original sentence, which is used to guide the decision of which the words might be deleted or inserted with the soft attention mechanism under the sequence-to-sequence framework. We conduct experiments on two benchmark datasets for paraphrase generation, namely the MSCOCO and Quora dataset. The evaluation results demonstrate that our dictionary-guided editing networks outperforms the baseline methods.
Tasks	Paraphrase Generation
Published	2018-06-21
URL	http://arxiv.org/abs/1806.08077v1
PDF	http://arxiv.org/pdf/1806.08077v1.pdf
PWC	https://paperswithcode.com/paper/dictionary-guided-editing-networks-for
Repo
Framework

On Batch Orthogonalization Layers


Title	On Batch Orthogonalization Layers
Authors	Blanchette, Laganière
Abstract	Batch normalization has become ubiquitous in many state-of-the-art nets. It accelerates training and yields good performance results. However, there are various other alternatives to normalization, e.g. orthonormalization. The objective of this paper is to explore the possible alternatives to channel normalization with orthonormalization layers. The performance of the algorithms are compared together with BN with prescribed performance measures.
Tasks
Published	2018-12-07
URL	http://arxiv.org/abs/1812.03049v1
PDF	http://arxiv.org/pdf/1812.03049v1.pdf
PWC	https://paperswithcode.com/paper/on-batch-orthogonalization-layers
Repo
Framework

Dynamic Multi-Level Multi-Task Learning for Sentence Simplification


Title	Dynamic Multi-Level Multi-Task Learning for Sentence Simplification
Authors	Han Guo, Ramakanth Pasunuru, Mohit Bansal
Abstract	Sentence simplification aims to improve readability and understandability, based on several operations such as splitting, deletion, and paraphrasing. However, a valid simplified sentence should also be logically entailed by its input sentence. In this work, we first present a strong pointer-copy mechanism based sequence-to-sequence sentence simplification model, and then improve its entailment and paraphrasing capabilities via multi-task learning with related auxiliary tasks of entailment and paraphrase generation. Moreover, we propose a novel ‘multi-level’ layered soft sharing approach where each auxiliary task shares different (higher versus lower) level layers of the sentence simplification model, depending on the task’s semantic versus lexico-syntactic nature. We also introduce a novel multi-armed bandit based training approach that dynamically learns how to effectively switch across tasks during multi-task learning. Experiments on multiple popular datasets demonstrate that our model outperforms competitive simplification systems in SARI and FKGL automatic metrics, and human evaluation. Further, we present several ablation analyses on alternative layer sharing methods, soft versus hard sharing, dynamic multi-armed bandit sampling approaches, and our model’s learned entailment and paraphrasing skills.
Tasks	Multi-Task Learning, Paraphrase Generation
Published	2018-06-19
URL	http://arxiv.org/abs/1806.07304v1
PDF	http://arxiv.org/pdf/1806.07304v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-multi-level-multi-task-learning-for
Repo
Framework

A Distributed Extension of the Turing Machine


Title	A Distributed Extension of the Turing Machine
Authors	Luis A. Pineda
Abstract	The Turing Machine has two implicit properties that depend on its underlying notion of computing: the format is fully determinate and computations are information preserving. Distributed representations lack these properties and cannot be fully captured by Turing’s standard model. To address this limitation a distributed extension of the Turing Machine is introduced in this paper. In the extended machine, functions and abstractions are expressed extensionally and computations are entropic. The machine is applied to the definition of an associative memory, with its corresponding memory register, recognition and retrieval operations. The memory is tested with an experiment for storing and recognizing hand written digits with satisfactory results. The experiment can be seen as a proof of concept that information can be stored and processed effectively in a highly distributed fashion using a symbolic but not fully determinate format. The new machine augments the symbolic mode of computing with consequences on the way Church Thesis is understood. The paper is concluded with a discussion of some implications of the extended machine for Artificial Intelligence and Cognition.
Tasks
Published	2018-03-28
URL	http://arxiv.org/abs/1803.10648v1
PDF	http://arxiv.org/pdf/1803.10648v1.pdf
PWC	https://paperswithcode.com/paper/a-distributed-extension-of-the-turing-machine
Repo
Framework

Finite Time Adaptive Stabilization of LQ Systems


Title	Finite Time Adaptive Stabilization of LQ Systems
Authors	Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George Michailidis
Abstract	Stabilization of linear systems with unknown dynamics is a canonical problem in adaptive control. Since the lack of knowledge of system parameters can cause it to become destabilized, an adaptive stabilization procedure is needed prior to regulation. Therefore, the adaptive stabilization needs to be completed in finite time. In order to achieve this goal, asymptotic approaches are not very helpful. There are only a few existing non-asymptotic results and a full treatment of the problem is not currently available. In this work, leveraging the novel method of random linear feedbacks, we establish high probability guarantees for finite time stabilization. Our results hold for remarkably general settings because we carefully choose a minimal set of assumptions. These include stabilizability of the underlying system and restricting the degree of heaviness of the noise distribution. To derive our results, we also introduce a number of new concepts and technical tools to address regularity and instability of the closed-loop matrix.
Tasks
Published	2018-07-22
URL	http://arxiv.org/abs/1807.09120v1
PDF	http://arxiv.org/pdf/1807.09120v1.pdf
PWC	https://paperswithcode.com/paper/finite-time-adaptive-stabilization-of-lq
Repo
Framework

Tool Breakage Detection using Deep Learning


Title	Tool Breakage Detection using Deep Learning
Authors	Guang Li, Xin Yang, Duanbing Chen, Anxing Song, Yuke Fang, Junlin Zhou
Abstract	In manufacture, steel and other metals are mainly cut and shaped during the fabrication process by computer numerical control (CNC) machines. To keep high productivity and efficiency of the fabrication process, engineers need to monitor the real-time process of CNC machines, and the lifetime management of machine tools. In a real manufacturing process, breakage of machine tools usually happens without any indication, this problem seriously affects the fabrication process for many years. Previous studies suggested many different approaches for monitoring and detecting the breakage of machine tools. However, there still exists a big gap between academic experiments and the complex real fabrication processes such as the high demands of real-time detections, the difficulty in data acquisition and transmission. In this work, we use the spindle current approach to detect the breakage of machine tools, which has the high performance of real-time monitoring, low cost, and easy to install. We analyze the features of the current of a milling machine spindle through tools wearing processes, and then we predict the status of tool breakage by a convolutional neural network(CNN). In addition, we use a BP neural network to understand the reliability of the CNN. The results show that our CNN approach can detect tool breakage with an accuracy of 93%, while the best performance of BP is 80%.
Tasks
Published	2018-08-16
URL	http://arxiv.org/abs/1808.05347v1
PDF	http://arxiv.org/pdf/1808.05347v1.pdf
PWC	https://paperswithcode.com/paper/tool-breakage-detection-using-deep-learning
Repo
Framework

Neural Random Projections for Language Modelling


Title	Neural Random Projections for Language Modelling
Authors	Davide Nunes, Luis Antunes
Abstract	Neural network-based language models deal with data sparsity problems by mapping the large discrete space of words into a smaller continuous space of real-valued vectors. By learning distributed vector representations for words, each training sample informs the neural network model about a combinatorial number of other patterns. In this paper, we exploit the sparsity in natural language even further by encoding each unique input word using a fixed sparse random representation. These sparse codes are then projected onto a smaller embedding space which allows for the encoding of word occurrences from a possibly unknown vocabulary, along with the creation of more compact language models using a reduced number of parameters. We investigate the properties of our encoding mechanism empirically, by evaluating its performance on the widely used Penn Treebank corpus. We show that guaranteeing approximately equidistant (nearly orthogonal) vector representations for unique discrete inputs is enough to provide the neural network model with enough information to learn –and make use– of distributed representations for these inputs.
Tasks	Language Modelling
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00930v4
PDF	http://arxiv.org/pdf/1807.00930v4.pdf
PWC	https://paperswithcode.com/paper/neural-random-projections-for-language
Repo
Framework

Sample-Relaxed Two-Dimensional Color Principal Component Analysis for Face Recognition and Image Reconstruction


Title	Sample-Relaxed Two-Dimensional Color Principal Component Analysis for Face Recognition and Image Reconstruction
Authors	Meixiang Zhao, Zhigang Jia, Dunwei Gong
Abstract	A sample-relaxed two-dimensional color principal component analysis (SR-2DCPCA) approach is presented for face recognition and image reconstruction based on quaternion models. A relaxation vector is automatically generated according to the variances of training color face images with the same label. A sample-relaxed, low-dimensional covariance matrix is constructed based on all the training samples relaxed by a relaxation vector, and its eigenvectors corresponding to the $r$ largest eigenvalues are defined as the optimal projection. The SR-2DCPCA aims to enlarge the global variance rather than to maximize the variance of the projected training samples. The numerical results based on real face data sets validate that SR-2DCPCA has a higher recognition rate than state-of-the-art methods and is efficient in image reconstruction.
Tasks	Face Recognition, Image Reconstruction
Published	2018-03-10
URL	http://arxiv.org/abs/1803.03837v1
PDF	http://arxiv.org/pdf/1803.03837v1.pdf
PWC	https://paperswithcode.com/paper/sample-relaxed-two-dimensional-color
Repo
Framework

Multiplicative Updates for Convolutional NMF Under $β$-Divergence


Title	Multiplicative Updates for Convolutional NMF Under $β$-Divergence
Authors	Pedro J. Villasana T., Stanislaw Gorlow, Arvind T. Hariraman
Abstract	In this letter, we generalize the convolutional NMF by taking the $\beta$-divergence as the contrast function and present the correct multiplicative updates for its factors in closed form. The new updates unify the $\beta$-NMF and the convolutional NMF. We state why almost all of the existing updates are inexact and approximative w.r.t. the convolutional data model. We show that our updates are stable and that their convergence performance is consistent across the most common values of $\beta$.
Tasks
Published	2018-03-14
URL	http://arxiv.org/abs/1803.05159v2
PDF	http://arxiv.org/pdf/1803.05159v2.pdf
PWC	https://paperswithcode.com/paper/multiplicative-updates-for-convolutional-nmf
Repo
Framework

Diverse Online Feature Selection


Title	Diverse Online Feature Selection
Authors	Chapman Siu, Richard Yi Da Xu
Abstract	Online feature selection has been an active research area in recent years. We propose a novel diverse online feature selection method based on Determinantal Point Processes (DPP). Our model aims to provide diverse features which can be composed in either a supervised or unsupervised framework. The framework aims to promote diversity based on the kernel produced on a feature level, through at most three stages: feature sampling, local criteria and global criteria for feature selection. In the feature sampling, we sample incoming stream of features using conditional DPP. The local criteria is used to assess and select streamed features (i.e. only when they arrive), we use unsupervised scale invariant methods to remove redundant features and optionally supervised methods to introduce label information to assess relevant features. Lastly, the global criteria uses regularization methods to select a global optimal subset of features. This three stage procedure continues until there are no more features arriving or some predefined stopping condition is met. We demonstrate based on experiments conducted on that this approach yields better compactness, is comparable and in some instances outperforms other state-of-the-art online feature selection methods.
Tasks	Feature Selection, Point Processes
Published	2018-06-12
URL	http://arxiv.org/abs/1806.04308v3
PDF	http://arxiv.org/pdf/1806.04308v3.pdf
PWC	https://paperswithcode.com/paper/diverse-online-feature-selection
Repo
Framework

Interpretable VAEs for nonlinear group factor analysis


Title	Interpretable VAEs for nonlinear group factor analysis
Authors	Samuel Ainsworth, Nicholas Foti, Adrian KC Lee, Emily Fox
Abstract	Deep generative models have recently yielded encouraging results in producing subjectively realistic samples of complex data. Far less attention has been paid to making these generative models interpretable. In many scenarios, ranging from scientific applications to finance, the observed variables have a natural grouping. It is often of interest to understand systems of interaction amongst these groups, and latent factor models (LFMs) are an attractive approach. However, traditional LFMs are limited by assuming a linear correlation structure. We present an output interpretable VAE (oi-VAE) for grouped data that models complex, nonlinear latent-to-observed relationships. We combine a structured VAE comprised of group-specific generators with a sparsity-inducing prior. We demonstrate that oi-VAE yields meaningful notions of interpretability in the analysis of motion capture and MEG data. We further show that in these situations, the regularization inherent to oi-VAE can actually lead to improved generalization and learned generative processes.
Tasks	Motion Capture
Published	2018-02-17
URL	http://arxiv.org/abs/1802.06765v1
PDF	http://arxiv.org/pdf/1802.06765v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-vaes-for-nonlinear-group-factor
Repo
Framework

Pseudo Mask Augmented Object Detection


Title	Pseudo Mask Augmented Object Detection
Authors	Xiangyun Zhao, Shuang Liang, Yichen Wei
Abstract	In this work, we present a novel and effective framework to facilitate object detection with the instance-level segmentation information that is only supervised by bounding box annotation. Starting from the joint object detection and instance segmentation network, we propose to recursively estimate the pseudo ground-truth object masks from the instance-level object segmentation network training, and then enhance the detection network with top-down segmentation feedbacks. The pseudo ground truth mask and network parameters are optimized alternatively to mutually benefit each other. To obtain the promising pseudo masks in each iteration, we embed a graphical inference that incorporates the low-level image appearance consistency and the bounding box annotations to refine the segmentation masks predicted by the segmentation network. Our approach progressively improves the object detection performance by incorporating the detailed pixel-wise information learned from the weakly-supervised segmentation network. Extensive evaluation on the detection task in PASCAL VOC 2007 and 2012 [12] verifies that the proposed approach is effective.
Tasks	Instance Segmentation, Object Detection, Semantic Segmentation
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05858v2
PDF	http://arxiv.org/pdf/1803.05858v2.pdf
PWC	https://paperswithcode.com/paper/pseudo-mask-augmented-object-detection
Repo
Framework

Combining Bayesian Optimization and Lipschitz Optimization


Title	Combining Bayesian Optimization and Lipschitz Optimization
Authors	Mohamed Osama Ahmed, Sharan Vaswani, Mark Schmidt
Abstract	Bayesian optimization and Lipschitz optimization have developed alternative techniques for optimizing black-box functions. They each exploit a different form of prior about the function. In this work, we explore strategies to combine these techniques for better global optimization. In particular, we propose ways to use the Lipschitz continuity assumption within traditional BO algorithms, which we call Lipschitz Bayesian optimization (LBO). This approach does not increase the asymptotic runtime and in some cases drastically improves the performance (while in the worst case the performance is similar). Indeed, in a particular setting, we prove that using the Lipschitz information yields the same or a better bound on the regret compared to using Bayesian optimization on its own. Moreover, we propose a simple heuristics to estimate the Lipschitz constant, and prove that a growing estimate of the Lipschitz constant is in some sense “harmless”. Our experiments on 15 datasets with 4 acquisition functions show that in the worst case LBO performs similar to the underlying BO method while in some cases it performs substantially better. Thompson sampling in particular typically saw drastic improvements (as the Lipschitz information corrected for it’s well-known “over-exploration” phenomenon) and its LBO variant often outperformed other acquisition functions.
Tasks
Published	2018-10-10
URL	http://arxiv.org/abs/1810.04336v1
PDF	http://arxiv.org/pdf/1810.04336v1.pdf
PWC	https://paperswithcode.com/paper/combining-bayesian-optimization-and-lipschitz
Repo
Framework

Persistence paths and signature features in topological data analysis


Title	Persistence paths and signature features in topological data analysis
Authors	Ilya Chevyrev, Vidit Nanda, Harald Oberhauser
Abstract	We introduce a new feature map for barcodes that arise in persistent homology computation. The main idea is to first realize each barcode as a path in a convenient vector space, and to then compute its path signature which takes values in the tensor algebra of that vector space. The composition of these two operations - barcode to path, path to tensor series - results in a feature map that has several desirable properties for statistical learning, such as universality and characteristicness, and achieves state-of-the-art results on common classification benchmarks.
Tasks	Topological Data Analysis
Published	2018-06-01
URL	http://arxiv.org/abs/1806.00381v2
PDF	http://arxiv.org/pdf/1806.00381v2.pdf
PWC	https://paperswithcode.com/paper/persistence-paths-and-signature-features-in
Repo
Framework