January 30, 2020

3235 words 16 mins read

Paper Group ANR 200

Two-layer Residual Sparsifying Transform Learning for Image Reconstruction. Just Go with the Flow: Self-Supervised Scene Flow Estimation. Resource-Efficient Wearable Computing for Real-Time Reconfigurable Machine Learning: A Cascading Binary Classification. Learning Fast Magnetic Resonance Imaging. Incorporating Word and Subword Units in Unsupervis …

Two-layer Residual Sparsifying Transform Learning for Image Reconstruction


Title	Two-layer Residual Sparsifying Transform Learning for Image Reconstruction
Authors	Xuehang Zheng, Saiprasad Ravishankar, Yong Long, Marc Louis Klasky, Brendt Wohlberg
Abstract	Signal models based on sparsity, low-rank and other properties have been exploited for image reconstruction from limited and corrupted data in medical imaging and other computational imaging applications. In particular, sparsifying transform models have shown promise in various applications, and offer numerous advantages such as efficiencies in sparse coding and learning. This work investigates pre-learning a two-layer extension of the transform model for image reconstruction, wherein the transform domain or filtering residuals of the image are further sparsified in the second layer. The proposed block coordinate descent optimization algorithms involve highly efficient updates. Preliminary numerical experiments demonstrate the usefulness of a two-layer model over the previous related schemes for CT image reconstruction from low-dose measurements.
Tasks	Image Reconstruction
Published	2019-06-01
URL	https://arxiv.org/abs/1906.00165v2
PDF	https://arxiv.org/pdf/1906.00165v2.pdf
PWC	https://paperswithcode.com/paper/190600165
Repo
Framework

Just Go with the Flow: Self-Supervised Scene Flow Estimation


Title	Just Go with the Flow: Self-Supervised Scene Flow Estimation
Authors	Himangi Mittal, Brian Okorn, David Held
Abstract	When interacting with highly dynamic environments, scene flow allows autonomous systems to reason about the non-rigid motion of multiple independent objects. This is of particular interest in the field of autonomous driving, in which many cars, people, bicycles, and other objects need to be accurately tracked. Current state of the art methods require annotated scene flow data from autonomous driving scenes to train scene flow networks with supervised learning. As an alternative, we present a method of training scene flow that uses two self-supervised losses, based on nearest neighbors and cycle consistency. These self-supervised losses allow us to train our method on large unlabeled autonomous driving datasets; the resulting method matches current state-of-the-art supervised performance using no real world annotations and exceeds state-of-the-art performance when combining our self-supervised approach with supervised learning on a smaller labeled dataset.
Tasks	Autonomous Driving, Scene Flow Estimation
Published	2019-12-01
URL	https://arxiv.org/abs/1912.00497v1
PDF	https://arxiv.org/pdf/1912.00497v1.pdf
PWC	https://paperswithcode.com/paper/just-go-with-the-flow-self-supervised-scene
Repo
Framework

Resource-Efficient Wearable Computing for Real-Time Reconfigurable Machine Learning: A Cascading Binary Classification


Title	Resource-Efficient Wearable Computing for Real-Time Reconfigurable Machine Learning: A Cascading Binary Classification
Authors	Mahdi Pedram, Seyed Ali Rokni, Marjan Nourollahi, Houman Homayoun, Hassan Ghasemzadeh
Abstract	Advances in embedded systems have enabled integration of many lightweight sensory devices within our daily life. In particular, this trend has given rise to continuous expansion of wearable sensors in a broad range of applications from health and fitness monitoring to social networking and military surveillance. Wearables leverage machine learning techniques to profile behavioral routine of their end-users through activity recognition algorithms. Current research assumes that such machine learning algorithms are trained offline. In reality, however, wearables demand continuous reconfiguration of their computational algorithms due to their highly dynamic operation. Developing a personalized and adaptive machine learning model requires real-time reconfiguration of the model. Due to stringent computation and memory constraints of these embedded sensors, the training/re-training of the computational algorithms need to be memory- and computation-efficient. In this paper, we propose a framework, based on the notion of online learning, for real-time and on-device machine learning training. We propose to transform the activity recognition problem from a multi-class classification problem to a hierarchical model of binary decisions using cascading online binary classifiers. Our results, based on Pegasos online learning, demonstrate that the proposed approach achieves 97% accuracy in detecting activities of varying intensities using a limited memory while power usages of the system is reduced by more than 40%.
Tasks	Activity Recognition
Published	2019-07-07
URL	https://arxiv.org/abs/1907.03250v1
PDF	https://arxiv.org/pdf/1907.03250v1.pdf
PWC	https://paperswithcode.com/paper/resource-efficient-wearable-computing-for
Repo
Framework

Learning Fast Magnetic Resonance Imaging


Title	Learning Fast Magnetic Resonance Imaging
Authors	Tomer Weiss, Sanketh Vedula, Ortal Senouf, Alex Bronstein, Oleg Michailovich, Michael Zibulevsky
Abstract	Magnetic Resonance Imaging (MRI) is considered today the golden-standard modality for soft tissues. The long acquisition times, however, make it more prone to motion artifacts as well as contribute to the relatively high costs of this examination. Over the years, multiple studies concentrated on designing reduced measurement schemes and image reconstruction schemes for MRI, however, these problems have been so far addressed separately. On the other hand, recent works in optical computational imaging have demonstrated growing success of the simultaneous learning-based design of the acquisition and reconstruction schemes manifesting significant improvement in the reconstruction quality with a constrained time budget. Inspired by these successes, in this work, we propose to learn accelerated MR acquisition schemes (in the form of Cartesian trajectories) jointly with the image reconstruction operator. To this end, we propose an algorithm for training the combined acquisition-reconstruction pipeline end-to-end in a differentiable way. We demonstrate the significance of using the learned Cartesian trajectories at different speed up rates.
Tasks	Image Reconstruction
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09324v1
PDF	https://arxiv.org/pdf/1905.09324v1.pdf
PWC	https://paperswithcode.com/paper/learning-fast-magnetic-resonance-imaging
Repo
Framework

Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring


Title	Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring
Authors	Zihan Liu, Yan Xu, Genta Indra Winata, Pascale Fung
Abstract	This paper describes CAiRE’s submission to the unsupervised machine translation track of the WMT’19 news shared task from German to Czech. We leverage a phrase-based statistical machine translation (PBSMT) model and a pre-trained language model to combine word-level neural machine translation (NMT) and subword-level NMT models without using any parallel data. We propose to solve the morphological richness problem of languages by training byte-pair encoding (BPE) embeddings for German and Czech separately, and they are aligned using MUSE (Conneau et al., 2018). To ensure the fluency and consistency of translations, a rescoring mechanism is proposed that reuses the pre-trained language model to select the translation candidates generated through beam search. Moreover, a series of pre-processing and post-processing approaches are applied to improve the quality of final translations.
Tasks	Language Modelling, Machine Translation, Unsupervised Machine Translation
Published	2019-08-16
URL	https://arxiv.org/abs/1908.05925v2
PDF	https://arxiv.org/pdf/1908.05925v2.pdf
PWC	https://paperswithcode.com/paper/incorporating-word-and-subword-units-in
Repo
Framework

Custom Video-Oculography Device and Its Application to Fourth Purkinje Image Detection during Saccades


Title	Custom Video-Oculography Device and Its Application to Fourth Purkinje Image Detection during Saccades
Authors	Evgeniy Abdulin, Lee Friedman, Oleg Komogortsev
Abstract	We built a custom video-based eye-tracker that saves every video frame as a full resolution image (MJPEG). Images can be processed offline for the detection of ocular features, including the pupil and corneal reflection (First Purkinje Image, P1) position. A comparison of multiple algorithms for detection of pupil and corneal reflection can be performed. The system provides for highly flexible stimulus creation, with mixing of graphic, image, and video stimuli. We can change cameras and infrared illuminators depending on the image qualities and frame rate desired. Using this system, we have detected the position of the Fourth Purkinje image (P4) in the frames. We show that when we estimate gaze by calculating P1-P4, signal compares well with gaze estimated with a DPI eye-tracker, which natively detects and tracks the P1 and P4.
Tasks
Published	2019-04-15
URL	http://arxiv.org/abs/1904.07361v1
PDF	http://arxiv.org/pdf/1904.07361v1.pdf
PWC	https://paperswithcode.com/paper/custom-video-oculography-device-and-its
Repo
Framework

Reconstruction-Aware Imaging System Ranking by use of a Sparsity-Driven Numerical Observer Enabled by Variational Bayesian Inference


Title	Reconstruction-Aware Imaging System Ranking by use of a Sparsity-Driven Numerical Observer Enabled by Variational Bayesian Inference
Authors	Yujia Chen, Yang Lou, Kun Wang, Matthew A. Kupinski, Mark A. Anastasio
Abstract	It is widely accepted that optimization of imaging system performance should be guided by task-based measures of image quality (IQ). It has been advocated that imaging hardware or data-acquisition designs should be optimized by use of an ideal observer (IO) that exploits full statistical knowledge of the measurement noise and class of objects to be imaged, without consideration of the reconstruction method. In practice, accurate and tractable models of the complete object statistics are often difficult to determine. Moreover, in imaging systems that employ compressive sensing concepts, imaging hardware and sparse image reconstruction are innately coupled technologies. In this work, a sparsity-driven observer (SDO) that can be employed to optimize hardware by use of a stochastic object model describing object sparsity is described and investigated. The SDO and sparse reconstruction method can therefore be “matched” in the sense that they both utilize the same statistical information regarding the class of objects to be imaged. To efficiently compute the SDO test statistic, computational tools developed recently for variational Bayesian inference with sparse linear models are adopted. The use of the SDO to rank data-acquisition designs in a stylized example as motivated by magnetic resonance imaging (MRI) is demonstrated. This study reveals that the SDO can produce rankings that are consistent with visual assessments of the reconstructed images but different from those produced by use of the traditionally employed Hotelling observer (HO).
Tasks	Bayesian Inference, Compressive Sensing, Image Reconstruction
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05820v1
PDF	https://arxiv.org/pdf/1905.05820v1.pdf
PWC	https://paperswithcode.com/paper/reconstruction-aware-imaging-system-ranking
Repo
Framework

Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size


Title	Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size
Authors	Ke Ma, Jinshan Zeng, Qianqian Xu, Xiaochun Cao, Wei Liu, Yuan Yao
Abstract	Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years. Most of the existing methods are based on semi-definite programming (\textit{SDP}), which is generally time-consuming and degrades the scalability, especially confronting large-scale data. To overcome this challenge, we propose a stochastic algorithm called \textit{SVRG-SBB}, which has the following features: i) achieving good scalability via dropping positive semi-definite (\textit{PSD}) constraints as serving a fast algorithm, i.e., stochastic variance reduced gradient (\textit{SVRG}) method, and ii) adaptive learning via introducing a new, adaptive step size called the stabilized Barzilai-Borwein (\textit{SBB}) step size. Theoretically, under some natural assumptions, we show the $\boldsymbol{O}(\frac{1}{T})$ rate of convergence to a stationary point of the proposed algorithm, where $T$ is the number of total iterations. Under the further Polyak-\L{}ojasiewicz assumption, we can show the global linear convergence (i.e., exponentially fast converging to a global optimum) of the proposed algorithm. Numerous simulations and real-world data experiments are conducted to show the effectiveness of the proposed algorithm by comparing with the state-of-the-art methods, notably, much lower computational cost with good prediction performance.
Tasks
Published	2019-12-01
URL	https://arxiv.org/abs/1912.00362v1
PDF	https://arxiv.org/pdf/1912.00362v1.pdf
PWC	https://paperswithcode.com/paper/fast-stochastic-ordinal-embedding-with
Repo
Framework

SEMA: an Extended Semantic Evaluation Metric for AMR


Title	SEMA: an Extended Semantic Evaluation Metric for AMR
Authors	Rafael T. Anchieta, Marco A. S. Cabezudo, Thiago A. S. Pardo
Abstract	Abstract Meaning Representation (AMR) is a recently designed semantic representation language intended to capture the meaning of a sentence, which may be represented as a single-rooted directed acyclic graph with labeled nodes and edges. The automatic evaluation of this structure plays an important role in the development of better systems, as well as for semantic annotation. Despite there is one available metric, smatch, it has some drawbacks. For instance, smatch creates a self-relation on the root of the graph, has weights for different error types, and does not take into account the dependence of the elements in the AMR structure. With these drawbacks, smatch masks several problems of the AMR parsers and distorts the evaluation of the AMRs. In view of this, in this paper, we introduce an extended metric to evaluate AMR parsers, which deals with the drawbacks of the smatch metric. Finally, we compare both metrics, using four well-known AMR parsers, and we argue that our metric is more refined, robust, fairer, and faster than smatch.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.12069v1
PDF	https://arxiv.org/pdf/1905.12069v1.pdf
PWC	https://paperswithcode.com/paper/sema-an-extended-semantic-evaluation-metric
Repo
Framework

A Novel Neural Network Structure Constructed according to Logical Relations


Title	A Novel Neural Network Structure Constructed according to Logical Relations
Authors	Wang Gang
Abstract	To solve more complex things, computer systems becomes more and more complex. It becomes harder to be handled manually for various conditions and unknown new conditions in advance. This situation urgently requires the development of computer technology of automatic judgement and decision according to various conditions. Current ANN (Artificial Neural Network) models are good at perceptual intelligence while they are not good at cognitive intelligence such as logical representation, making them not deal with the above situation well. Therefore, researchers have tried to design novel models so as to represent and store logical relations into the neural network structures, the type of which is called KBNN (Knowledge-Based Neural Network). In this type models, the neurons and links are designed specific for logical relation representation, and the neural network structures are constructed according to logical relations, allowing us to construct automatically the rule libraries of expert systems. In this paper, the further improvement is made based on KBNN by redesigning the neurons and links. This improvement can make neurons solely for representing things while making links solely for representing logical relations between things, and thus no extra logical neurons are needed. Moreover, the related construction and adjustment methods of the neural network structure are also designed based on the redesigned neurons and links, making the neural network structure dynamically constructed and adjusted according to the logical relations. The probabilistic mechanism for the weight adjustment can make the neural network model further represent logical relations in the uncertainty.
Tasks
Published	2019-03-07
URL	http://arxiv.org/abs/1903.02683v1
PDF	http://arxiv.org/pdf/1903.02683v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-neural-network-structure-constructed
Repo
Framework

Discussing the Feasibility of Acoustic Sensors for Side Channel-aided Industrial Intrusion Detection: An Essay


Title	Discussing the Feasibility of Acoustic Sensors for Side Channel-aided Industrial Intrusion Detection: An Essay
Authors	Simon D. Duque Anton, Anna Pia Lohfink, Hans Dieter Schotten
Abstract	The fourth industrial revolution leads to an increased use of embedded computation and intercommunication in an industrial environment. While reducing cost and effort for set up, operation and maintenance, and increasing the time to operation or market respectively as well as the efficiency, this also increases the attack surface of enterprises. Industrial enterprises have become targets of cyber criminals in the last decade, reasons being espionage but also politically motivated. Infamous attack campaigns as well as easily available malware that hits industry in an unprepared state create a large threat landscape. As industrial systems often operate for many decades and are difficult or impossible to upgrade in terms of security, legacy-compatible industrial security solutions are necessary in order to create a security parameter. One plausible approach in industry is the implementation and employment of side-channel sensors. Combining readily available sensor data from different sources via different channels can provide an enhanced insight about the security state. In this work, a data set of an experimental industrial set up containing side channel sensors is discussed conceptually and insights are derived.
Tasks	Intrusion Detection
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03753v1
PDF	https://arxiv.org/pdf/1909.03753v1.pdf
PWC	https://paperswithcode.com/paper/discussing-the-feasibility-of-acoustic
Repo
Framework

Contrastive Language Adaptation for Cross-Lingual Stance Detection


Title	Contrastive Language Adaptation for Cross-Lingual Stance Detection
Authors	Mitra Mohtarami, James Glass, Preslav Nakov
Abstract	We study cross-lingual stance detection, which aims to leverage labeled data in one language to identify the relative perspective (or stance) of a given document with respect to a claim in a different target language. In particular, we introduce a novel contrastive language adaptation approach applied to memory networks, which ensures accurate alignment of stances in the source and target languages, and can effectively deal with the challenge of limited labeled data in the target language. The evaluation results on public benchmark datasets and comparison against current state-of-the-art approaches demonstrate the effectiveness of our approach.
Tasks	Stance Detection
Published	2019-10-04
URL	https://arxiv.org/abs/1910.02076v1
PDF	https://arxiv.org/pdf/1910.02076v1.pdf
PWC	https://paperswithcode.com/paper/contrastive-language-adaptation-for-cross
Repo
Framework

Probabilistic Verification and Reachability Analysis of Neural Networks via Semidefinite Programming


Title	Probabilistic Verification and Reachability Analysis of Neural Networks via Semidefinite Programming
Authors	Mahyar Fazlyab, Manfred Morari, George J. Pappas
Abstract	Quantifying the robustness of neural networks or verifying their safety properties against input uncertainties or adversarial attacks have become an important research area in learning-enabled systems. Most results concentrate around the worst-case scenario where the input of the neural network is perturbed within a norm-bounded uncertainty set. In this paper, we consider a probabilistic setting in which the uncertainty is random with known first two moments. In this context, we discuss two relevant problems: (i) probabilistic safety verification, in which the goal is to find an upper bound on the probability of violating a safety specification; and (ii) confidence ellipsoid estimation, in which given a confidence ellipsoid for the input of the neural network, our goal is to compute a confidence ellipsoid for the output. Due to the presence of nonlinear activation functions, these two problems are very difficult to solve exactly. To simplify the analysis, our main idea is to abstract the nonlinear activation functions by a combination of affine and quadratic constraints they impose on their input-output pairs. We then show that the safety of the abstracted network, which is sufficient for the safety of the original network, can be analyzed using semidefinite programming. We illustrate the performance of our approach with numerical experiments.
Tasks
Published	2019-10-09
URL	https://arxiv.org/abs/1910.04249v1
PDF	https://arxiv.org/pdf/1910.04249v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-verification-and-reachability
Repo
Framework

3D Face Mask Presentation Attack Detection Based on Intrinsic Image Analysis


Title	3D Face Mask Presentation Attack Detection Based on Intrinsic Image Analysis
Authors	Lei Li, Zhaoqiang Xia, Xiaoyue Jiang, Yupeng Ma, Fabio Roli, Xiaoyi Feng
Abstract	Face presentation attacks have become a major threat to face recognition systems and many countermeasures have been proposed in the past decade. However, most of them are devoted to 2D face presentation attacks, rather than 3D face masks. Unlike the real face, the 3D face mask is usually made of resin materials and has a smooth surface, resulting in reflectance differences. So, we propose a novel detection method for 3D face mask presentation attack by modeling reflectance differences based on intrinsic image analysis. In the proposed method, the face image is first processed with intrinsic image decomposition to compute its reflectance image. Then, the intensity distribution histograms are extracted from three orthogonal planes to represent the intensity differences of reflectance images between the real face and 3D face mask. After that, the 1D convolutional network is further used to capture the information for describing different materials or surfaces react differently to changes in illumination. Extensive experiments on the 3DMAD database demonstrate the effectiveness of our proposed method in distinguishing a face mask from the real one and show that the detection performance outperforms other state-of-the-art methods.
Tasks	Face Recognition, Intrinsic Image Decomposition
Published	2019-03-27
URL	http://arxiv.org/abs/1903.11303v1
PDF	http://arxiv.org/pdf/1903.11303v1.pdf
PWC	https://paperswithcode.com/paper/3d-face-mask-presentation-attack-detection
Repo
Framework

A Weakly-Supervised Attention-based Visualization Tool for Assessing Political Affiliation


Title	A Weakly-Supervised Attention-based Visualization Tool for Assessing Political Affiliation
Authors	Srijith Rajamohan, Alana Romanella, Amit Ramesh
Abstract	In this work, we seek to finetune a weakly-supervised expert-guided Deep Neural Network (DNN) for the purpose of determining political affiliations. In this context, stance detection is used for determining political affiliation or ideology which is framed in the form of relative proximities between entities in a low-dimensional space. An attention-based mechanism is used to provide model interpretability. A Deep Neural Network for Natural Language Understanding (NLU) using static and contextual embeddings is trained and evaluated. Various techniques to visualize the projections generated from the network are evaluated for visualization efficiency. An overview of the pipeline from data ingestion, processing and generation of visualization is given here. A web-based framework created to faciliate this interaction and exploration is presented here. Preliminary results of this study are summarized and future work is outlined.
Tasks	Stance Detection
Published	2019-08-05
URL	https://arxiv.org/abs/1908.02282v1
PDF	https://arxiv.org/pdf/1908.02282v1.pdf
PWC	https://paperswithcode.com/paper/a-weakly-supervised-attention-based
Repo
Framework