July 27, 2019

3041 words 15 mins read

Paper Group ANR 528

Discriminative Optimization: Theory and Applications to Computer Vision Problems. Interaction Information for Causal Inference: The Case of Directed Triangle. Phonological (un)certainty weights lexical activation. Anomaly Detection by Robust Statistics. Local Activity-tuned Image Filtering for Noise Removal and Image Smoothing. Using Transfer Learn …

Discriminative Optimization: Theory and Applications to Computer Vision Problems


Title	Discriminative Optimization: Theory and Applications to Computer Vision Problems
Authors	Jayakorn Vongkulbhisal, Fernando De la Torre, João P. Costeira
Abstract	Many computer vision problems are formulated as the optimization of a cost function. This approach faces two main challenges: (i) designing a cost function with a local optimum at an acceptable solution, and (ii) developing an efficient numerical method to search for one (or multiple) of these local optima. While designing such functions is feasible in the noiseless case, the stability and location of local optima are mostly unknown under noise, occlusion, or missing data. In practice, this can result in undesirable local optima or not having a local optimum in the expected place. On the other hand, numerical optimization algorithms in high-dimensional spaces are typically local and often rely on expensive first or second order information to guide the search. To overcome these limitations, this paper proposes Discriminative Optimization (DO), a method that learns search directions from data without the need of a cost function. Specifically, DO explicitly learns a sequence of updates in the search space that leads to stationary points that correspond to desired solutions. We provide a formal analysis of DO and illustrate its benefits in the problem of 3D point cloud registration, camera pose estimation, and image denoising. We show that DO performed comparably or outperformed state-of-the-art algorithms in terms of accuracy, robustness to perturbations, and computational efficiency.
Tasks	Denoising, Image Denoising, Point Cloud Registration, Pose Estimation
Published	2017-07-13
URL	http://arxiv.org/abs/1707.04318v1
PDF	http://arxiv.org/pdf/1707.04318v1.pdf
PWC	https://paperswithcode.com/paper/discriminative-optimization-theory-and
Repo
Framework

Interaction Information for Causal Inference: The Case of Directed Triangle


Title	Interaction Information for Causal Inference: The Case of Directed Triangle
Authors	AmirEmad Ghassami, Negar Kiyavash
Abstract	Interaction information is one of the multivariate generalizations of mutual information, which expresses the amount information shared among a set of variables, beyond the information, which is shared in any proper subset of those variables. Unlike (conditional) mutual information, which is always non-negative, interaction information can be negative. We utilize this property to find the direction of causal influences among variables in a triangle topology under some mild assumptions.
Tasks	Causal Inference
Published	2017-01-30
URL	http://arxiv.org/abs/1701.08868v1
PDF	http://arxiv.org/pdf/1701.08868v1.pdf
PWC	https://paperswithcode.com/paper/interaction-information-for-causal-inference
Repo
Framework

Phonological (un)certainty weights lexical activation


Title	Phonological (un)certainty weights lexical activation
Authors	Laura Gwilliams, David Poeppel, Alec Marantz, Tal Linzen
Abstract	Spoken word recognition involves at least two basic computations. First is matching acoustic input to phonological categories (e.g. /b/, /p/, /d/). Second is activating words consistent with those phonological categories. Here we test the hypothesis that the listener’s probability distribution over lexical items is weighted by the outcome of both computations: uncertainty about phonological discretisation and the frequency of the selected word(s). To test this, we record neural responses in auditory cortex using magnetoencephalography, and model this activity as a function of the size and relative activation of lexical candidates. Our findings indicate that towards the beginning of a word, the processing system indeed weights lexical candidates by both phonological certainty and lexical frequency; however, later into the word, activation is weighted by frequency alone.
Tasks
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06729v1
PDF	http://arxiv.org/pdf/1711.06729v1.pdf
PWC	https://paperswithcode.com/paper/phonological-uncertainty-weights-lexical
Repo
Framework

Anomaly Detection by Robust Statistics


Title	Anomaly Detection by Robust Statistics
Authors	Peter J. Rousseeuw, Mia Hubert
Abstract	Real data often contain anomalous cases, also known as outliers. These may spoil the resulting analysis but they may also contain valuable information. In either case, the ability to detect such anomalies is essential. A useful tool for this purpose is robust statistics, which aims to detect the outliers by first fitting the majority of the data and then flagging data points that deviate from it. We present an overview of several robust methods and the resulting graphical outlier detection tools. We discuss robust procedures for univariate, low-dimensional, and high-dimensional data, such as estimating location and scatter, linear regression, principal component analysis, classification, clustering, and functional data analysis. Also the challenging new topic of cellwise outliers is introduced.
Tasks	Anomaly Detection, Outlier Detection
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09752v2
PDF	http://arxiv.org/pdf/1707.09752v2.pdf
PWC	https://paperswithcode.com/paper/anomaly-detection-by-robust-statistics
Repo
Framework

Local Activity-tuned Image Filtering for Noise Removal and Image Smoothing


Title	Local Activity-tuned Image Filtering for Noise Removal and Image Smoothing
Authors	Lijun Zhao, Jie Liang, Huihui Bai, Lili Meng, Anhong Wang, Yao Zhao
Abstract	In this paper, two local activity-tuned filtering frameworks are proposed for noise removal and image smoothing, where the local activity measurement is given by the clipped and normalized local variance or standard deviation. The first framework is a modified anisotropic diffusion for noise removal of piece-wise smooth image. The second framework is a local activity-tuned Relative Total Variation (LAT-RTV) method for image smoothing. Both frameworks employ the division of gradient and the local activity measurement to achieve noise removal. In addition, to better capture local information, the proposed LAT-RTV uses the product of gradient and local activity measurement to boost the performance of image smoothing. Experimental results are presented to demonstrate the efficiency of the proposed methods on various applications, including depth image filtering, clip-art compression artifact removal, image smoothing, and image denoising.
Tasks	Denoising, Image Denoising
Published	2017-07-09
URL	http://arxiv.org/abs/1707.02637v4
PDF	http://arxiv.org/pdf/1707.02637v4.pdf
PWC	https://paperswithcode.com/paper/local-activity-tuned-image-filtering-for
Repo
Framework

Using Transfer Learning for Image-Based Cassava Disease Detection


Title	Using Transfer Learning for Image-Based Cassava Disease Detection
Authors	Amanda Ramcharan, Kelsee Baranowski, Peter McCloskey, Babuali Ahmed, James Legg, David Hughes
Abstract	Cassava is the third largest source of carbohydrates for human food in the world but is vulnerable to virus diseases, which threaten to destabilize food security in sub-Saharan Africa. Novel methods of cassava disease detection are needed to support improved control which will prevent this crisis. Image recognition offers both a cost effective and scalable technology for disease detection. New transfer learning methods offer an avenue for this technology to be easily deployed on mobile devices. Using a dataset of cassava disease images taken in the field in Tanzania, we applied transfer learning to train a deep convolutional neural network to identify three diseases and two types of pest damage (or lack thereof). The best trained model accuracies were 98% for brown leaf spot (BLS), 96% for red mite damage (RMD), 95% for green mite damage (GMD), 98% for cassava brown streak disease (CBSD), and 96% for cassava mosaic disease (CMD). The best model achieved an overall accuracy of 93% for data not used in the training process. Our results show that the transfer learning approach for image recognition of field images offers a fast, affordable, and easily deployable strategy for digital plant disease detection.
Tasks	Transfer Learning
Published	2017-06-19
URL	http://arxiv.org/abs/1707.03717v2
PDF	http://arxiv.org/pdf/1707.03717v2.pdf
PWC	https://paperswithcode.com/paper/using-transfer-learning-for-image-based
Repo
Framework

High-Throughput and Language-Agnostic Entity Disambiguation and Linking on User Generated Data


Title	High-Throughput and Language-Agnostic Entity Disambiguation and Linking on User Generated Data
Authors	Preeti Bhargava, Nemanja Spasojevic, Guoning Hu
Abstract	The Entity Disambiguation and Linking (EDL) task matches entity mentions in text to a unique Knowledge Base (KB) identifier such as a Wikipedia or Freebase id. It plays a critical role in the construction of a high quality information network, and can be further leveraged for a variety of information retrieval and NLP tasks such as text categorization and document tagging. EDL is a complex and challenging problem due to ambiguity of the mentions and real world text being multi-lingual. Moreover, EDL systems need to have high throughput and should be lightweight in order to scale to large datasets and run on off-the-shelf machines. More importantly, these systems need to be able to extract and disambiguate dense annotations from the data in order to enable an Information Retrieval or Extraction task running on the data to be more efficient and accurate. In order to address all these challenges, we present the Lithium EDL system and algorithm - a high-throughput, lightweight, language-agnostic EDL system that extracts and correctly disambiguates 75% more entities than state-of-the-art EDL systems and is significantly faster than them.
Tasks	Entity Disambiguation, Information Retrieval, Text Categorization
Published	2017-03-13
URL	http://arxiv.org/abs/1703.04498v1
PDF	http://arxiv.org/pdf/1703.04498v1.pdf
PWC	https://paperswithcode.com/paper/high-throughput-and-language-agnostic-entity
Repo
Framework

On the Complexity of CCG Parsing


Title	On the Complexity of CCG Parsing
Authors	Marco Kuhlmann, Giorgio Satta, Peter Jonsson
Abstract	We study the parsing complexity of Combinatory Categorial Grammar (CCG) in the formalism of Vijay-Shanker and Weir (1994). As our main result, we prove that any parsing algorithm for this formalism will take in the worst case exponential time when the size of the grammar, and not only the length of the input sentence, is included in the analysis. This sets the formalism of Vijay-Shanker and Weir (1994) apart from weakly equivalent formalisms such as Tree-Adjoining Grammar (TAG), for which parsing can be performed in time polynomial in the combined size of grammar and input sentence. Our results contribute to a refined understanding of the class of mildly context-sensitive grammars, and inform the search for new, mildly context-sensitive versions of CCG.
Tasks
Published	2017-02-21
URL	http://arxiv.org/abs/1702.06594v2
PDF	http://arxiv.org/pdf/1702.06594v2.pdf
PWC	https://paperswithcode.com/paper/on-the-complexity-of-ccg-parsing
Repo
Framework

Benchmarking Denoising Algorithms with Real Photographs


Title	Benchmarking Denoising Algorithms with Real Photographs
Authors	Tobias Plötz, Stefan Roth
Abstract	Lacking realistic ground truth data, image denoising techniques are traditionally evaluated on images corrupted by synthesized i.i.d. Gaussian noise. We aim to obviate this unrealistic setting by developing a methodology for benchmarking denoising techniques on real photographs. We capture pairs of images with different ISO values and appropriately adjusted exposure times, where the nearly noise-free low-ISO image serves as reference. To derive the ground truth, careful post-processing is needed. We correct spatial misalignment, cope with inaccuracies in the exposure parameters through a linear intensity transform based on a novel heteroscedastic Tobit regression model, and remove residual low-frequency bias that stems, e.g., from minor illumination changes. We then capture a novel benchmark dataset, the Darmstadt Noise Dataset (DND), with consumer cameras of differing sensor sizes. One interesting finding is that various recent techniques that perform well on synthetic noise are clearly outperformed by BM3D on photographs with real noise. Our benchmark delineates realistic evaluation scenarios that deviate strongly from those commonly used in the scientific literature.
Tasks	Denoising, Image Denoising
Published	2017-07-05
URL	http://arxiv.org/abs/1707.01313v1
PDF	http://arxiv.org/pdf/1707.01313v1.pdf
PWC	https://paperswithcode.com/paper/benchmarking-denoising-algorithms-with-real
Repo
Framework

The signature of robot action success in EEG signals of a human observer: Decoding and visualization using deep convolutional neural networks


Title	The signature of robot action success in EEG signals of a human observer: Decoding and visualization using deep convolutional neural networks
Authors	Joos Behncke, Robin Tibor Schirrmeister, Wolfram Burgard, Tonio Ball
Abstract	The importance of robotic assistive devices grows in our work and everyday life. Cooperative scenarios involving both robots and humans require safe human-robot interaction. One important aspect here is the management of robot errors, including fast and accurate online robot-error detection and correction. Analysis of brain signals from a human interacting with a robot may help identifying robot errors, but accuracies of such analyses have still substantial space for improvement. In this paper we evaluate whether a novel framework based on deep convolutional neural networks (deep ConvNets) could improve the accuracy of decoding robot errors from the EEG of a human observer, both during an object grasping and a pouring task. We show that deep ConvNets reached significantly higher accuracies than both regularized Linear Discriminant Analysis (rLDA) and filter bank common spatial patterns (FB-CSP) combined with rLDA, both widely used EEG classifiers. Deep ConvNets reached mean accuracies of 75% +/- 9 %, rLDA 65% +/- 10% and FB-CSP + rLDA 63% +/- 6% for decoding of erroneous vs. correct trials. Visualization of the time-domain EEG features learned by the ConvNets to decode errors revealed spatiotemporal patterns that reflected differences between the two experimental paradigms. Across subjects, ConvNet decoding accuracies were significantly correlated with those obtained with rLDA, but not CSP, indicating that in the present context ConvNets behaved more ‘rLDA-like’ (but consistently better), while in a previous decoding study with another task but the same ConvNet architecture, it was found to behave more ‘CSP-like’. Our findings thus provide further support for the assumption that deep ConvNets are a versatile addition to the existing toolbox of EEG decoding techniques, and we discuss steps how ConvNet EEG decoding performance could be further optimized.
Tasks	EEG, Eeg Decoding
Published	2017-11-16
URL	http://arxiv.org/abs/1711.06068v1
PDF	http://arxiv.org/pdf/1711.06068v1.pdf
PWC	https://paperswithcode.com/paper/the-signature-of-robot-action-success-in-eeg
Repo
Framework

Photosensor Oculography: Survey and Parametric Analysis of Designs using Model-Based Simulation


Title	Photosensor Oculography: Survey and Parametric Analysis of Designs using Model-Based Simulation
Authors	Ioannis Rigas, Hayes Raffle, Oleg V. Komogortsev
Abstract	This paper presents a renewed overview of photosensor oculography (PSOG), an eye-tracking technique based on the principle of using simple photosensors to measure the amount of reflected (usually infrared) light when the eye rotates. Photosensor oculography can provide measurements with high precision, low latency and reduced power consumption, and thus it appears as an attractive option for performing eye-tracking in the emerging head-mounted interaction devices, e.g. augmented and virtual reality (AR/VR) headsets. In our current work we employ an adjustable simulation framework as a common basis for performing an exploratory study of the eye-tracking behavior of different photosensor oculography designs. With the performed experiments we explore the effects from the variation of some basic parameters of the designs on the resulting accuracy and cross-talk, which are crucial characteristics for the seamless operation of human-computer interaction applications based on eye-tracking. Our experimental results reveal the design trade-offs that need to be adopted to tackle the competing conditions that lead to optimum performance of different eye-tracking characteristics. We also present the transformations that arise in the eye-tracking output when sensor shifts occur, and assess the resulting degradation in accuracy for different combinations of eye movements and sensor shifts.
Tasks	Eye Tracking
Published	2017-07-17
URL	http://arxiv.org/abs/1707.05413v2
PDF	http://arxiv.org/pdf/1707.05413v2.pdf
PWC	https://paperswithcode.com/paper/photosensor-oculography-survey-and-parametric
Repo
Framework

Automated Unsupervised Segmentation of Liver Lesions in CT scans via Cahn-Hilliard Phase Separation


Title	Automated Unsupervised Segmentation of Liver Lesions in CT scans via Cahn-Hilliard Phase Separation
Authors	Jana Lipková, Markus Rempfler, Patrick Christ, John Lowengrub, Bjoern H. Menze
Abstract	The segmentation of liver lesions is crucial for detection, diagnosis and monitoring progression of liver cancer. However, design of accurate automated methods remains challenging due to high noise in CT scans, low contrast between liver and lesions, as well as large lesion variability. We propose a 3D automatic, unsupervised method for liver lesions segmentation using a phase separation approach. It is assumed that liver is a mixture of two phases: healthy liver and lesions, represented by different image intensities polluted by noise. The Cahn-Hilliard equation is used to remove the noise and separate the mixture into two distinct phases with well-defined interfaces. This simplifies the lesion detection and segmentation task drastically and enables to segment liver lesions by thresholding the Cahn-Hilliard solution. The method was tested on 3Dircadb and LITS dataset.
Tasks
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02348v1
PDF	http://arxiv.org/pdf/1704.02348v1.pdf
PWC	https://paperswithcode.com/paper/automated-unsupervised-segmentation-of-liver
Repo
Framework

NileTMRG at SemEval-2017 Task 4: Arabic Sentiment Analysis


Title	NileTMRG at SemEval-2017 Task 4: Arabic Sentiment Analysis
Authors	Samhaa R. El-Beltagy, Mona El Kalamawy, Abu Bakr Soliman
Abstract	This paper describes two systems that were used by the authors for addressing Arabic Sentiment Analysis as part of SemEval-2017, task 4. The authors participated in three Arabic related subtasks which are: Subtask A (Message Polarity Classification), Sub-task B (Topic-Based Message Polarity classification) and Subtask D (Tweet quantification) using the team name of NileTMRG. For subtask A, we made use of our previously developed sentiment analyzer which we augmented with a scored lexicon. For subtasks B and D, we used an ensemble of three different classifiers. The first classifier was a convolutional neural network for which we trained (word2vec) word embeddings. The second classifier consisted of a MultiLayer Perceptron, while the third classifier was a Logistic regression model that takes the same input as the second classifier. Voting between the three classifiers was used to determine the final outcome. The output from task B, was quantified to produce the results for task D. In all three Arabic related tasks in which NileTMRG participated, the team ranked at number one.
Tasks	Arabic Sentiment Analysis, Sentiment Analysis, Word Embeddings
Published	2017-10-23
URL	http://arxiv.org/abs/1710.08458v1
PDF	http://arxiv.org/pdf/1710.08458v1.pdf
PWC	https://paperswithcode.com/paper/niletmrg-at-semeval-2017-task-4-arabic
Repo
Framework

Using the quantization error from Self-Organized Map (SOM) output for detecting critical variability in large bodies of image time series in less than a minute


Title	Using the quantization error from Self-Organized Map (SOM) output for detecting critical variability in large bodies of image time series in less than a minute
Authors	Birgitta Dresp-Langley, John Mwangi Wandeto
Abstract	The quantization error (QE) from SOM applied on time series of spatial contrast images with variable relative amount of white and dark pixel contents, as in monochromatic medical images or satellite images, is proven a reliable indicator of potentially critical changes in image homogeneity. The QE is shown to increase linearly with the variability in spatial contrast contents across time when contrast intensity is kept constant.
Tasks	Quantization, Time Series
Published	2017-10-29
URL	http://arxiv.org/abs/1710.10648v1
PDF	http://arxiv.org/pdf/1710.10648v1.pdf
PWC	https://paperswithcode.com/paper/using-the-quantization-error-from-self
Repo
Framework

Efficient Defenses Against Adversarial Attacks


Title	Efficient Defenses Against Adversarial Attacks
Authors	Valentina Zantedeschi, Maria-Irina Nicolae, Ambrish Rawat
Abstract	Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention of undermining a system. In the case of DNNs, the lack of better understanding of their working has prevented the development of efficient defenses. In this paper, we propose a new defense method based on practical observations which is easy to integrate into models and performs better than state-of-the-art defenses. Our proposed solution is meant to reinforce the structure of a DNN, making its prediction more stable and less likely to be fooled by adversarial samples. We conduct an extensive experimental study proving the efficiency of our method against multiple attacks, comparing it to numerous defenses, both in white-box and black-box setups. Additionally, the implementation of our method brings almost no overhead to the training procedure, while maintaining the prediction performance of the original model on clean samples.
Tasks
Published	2017-07-21
URL	http://arxiv.org/abs/1707.06728v2
PDF	http://arxiv.org/pdf/1707.06728v2.pdf
PWC	https://paperswithcode.com/paper/efficient-defenses-against-adversarial
Repo
Framework