January 30, 2020

3233 words 16 mins read

Paper Group ANR 332

Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition. Exact Recovery of Tensor Robust Principal Component Analysis under Linear Transforms. Long-Bone Fracture Detection using Artificial Neural Networks based on Line Features of X-ray Images. Hidden Markov Models derived from Behavior Trees. CircConv: A Structured Convolution …

Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition


Title	Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition
Authors	Ping Hu, Ximeng Sun, Kate Saenko, Stan Sclaroff
Abstract	Learning from a few examples is a challenging task for machine learning. While recent progress has been made for this problem, most of the existing methods ignore the compositionality in visual concept representation (e.g. objects are built from parts or composed of semantic attributes), which is key to the human ability to easily learn from a small number of examples. To enhance the few-shot learning models with compositionality, in this paper we present the simple yet powerful Compositional Feature Aggregation (CFA) module as a weakly-supervised regularization for deep networks. Given the deep feature maps extracted from the input, our CFA module first disentangles the feature space into disjoint semantic subspaces that model different attributes, and then bilinearly aggregates the local features within each of these subspaces. CFA explicitly regularizes the representation with both semantic and spatial compositionality to produce discriminative representations for few-shot recognition tasks. Moreover, our method does not need any supervision for attributes and object parts during training, thus can be conveniently plugged into existing models for end-to-end optimization while keeping the model size and computation cost nearly the same. Extensive experiments on few-shot image classification and action recognition tasks demonstrate that our method provides substantial improvements over recent state-of-the-art methods.
Tasks	Few-Shot Image Classification, Few-Shot Learning, Image Classification
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04833v1
PDF	https://arxiv.org/pdf/1906.04833v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-compositional
Repo
Framework

Exact Recovery of Tensor Robust Principal Component Analysis under Linear Transforms


Title	Exact Recovery of Tensor Robust Principal Component Analysis under Linear Transforms
Authors	Canyi Lu, Pan Zhou
Abstract	This work studies the Tensor Robust Principal Component Analysis (TRPCA) problem, which aims to exactly recover the low-rank and sparse components from their sum. Our model is motivated by the recently proposed linear transforms based tensor-tensor product and tensor SVD. We define a new transforms depended tensor rank and the corresponding tensor nuclear norm. Then we solve the TRPCA problem by convex optimization whose objective is a weighted combination of the new tensor nuclear norm and the $\ell_1$-norm. In theory, we show that under certain incoherence conditions, the convex program exactly recovers the underlying low-rank and sparse components. It is of great interest that our new TRPCA model generalizes existing works. In particular, if the studied tensor reduces to a matrix, our TRPCA model reduces to the known matrix RPCA. Our new TRPCA which is allowed to use general linear transforms can be regarded as an extension of our former TRPCA work which uses the discrete Fourier transform. But their proof of the recovery guarantee is different. Numerical experiments verify our results and the application on image recovery demonstrates the superiority of our method.
Tasks
Published	2019-07-16
URL	https://arxiv.org/abs/1907.08288v1
PDF	https://arxiv.org/pdf/1907.08288v1.pdf
PWC	https://paperswithcode.com/paper/exact-recovery-of-tensor-robust-principal
Repo
Framework

Long-Bone Fracture Detection using Artificial Neural Networks based on Line Features of X-ray Images


Title	Long-Bone Fracture Detection using Artificial Neural Networks based on Line Features of X-ray Images
Authors	Alice Yi Yang, Ling Cheng
Abstract	Two line-based fracture detection scheme are developed and discussed, namely Standard line-based fracture detection and Adaptive Differential Parameter Optimized (ADPO) line-based fracture detection. The purpose for the two line-based fracture detection schemes is to detect fractured lines from X-ray images using extracted features based on recognised patterns to differentiate fractured lines from non-fractured lines. The difference between the two schemes is the detection of detailed lines. The ADPO scheme optimizes the parameters of the Probabilistic Hough Transform, such that granule lines within the fractured regions are detected, whereas the Standard scheme is unable to detect them. The lines are detected using the Probabilistic Hough Function, in which the detected lines are a representation of the image edge objects. The lines are given in the form of points, (x,y), which includes the starting and ending point. Based on the given line points, 13 features are extracted from each line, as a summary of line information. These features are used for fracture and non-fracture classification of the detected lines. The classification is carried out by the Artificial Neural Network (ANN). There are two evaluations that are employed to evaluate both the entirety of the system and the ANN. The Standard Scheme is capable of achieving an average accuracy of 74.25%, whilst the ADPO scheme achieved an average accuracy of 74.4%. The ADPO scheme is opted for over the Standard scheme, however it can be further improved with detected contours and its extracted features.
Tasks
Published	2019-02-20
URL	http://arxiv.org/abs/1902.07458v1
PDF	http://arxiv.org/pdf/1902.07458v1.pdf
PWC	https://paperswithcode.com/paper/long-bone-fracture-detection-using-artificial
Repo
Framework

Hidden Markov Models derived from Behavior Trees


Title	Hidden Markov Models derived from Behavior Trees
Authors	Blake Hannaford
Abstract	Behavior trees are rapidly attracting interest in robotics and human task-related motion tracking. However no algorithms currently exist to track or identify parameters of BTs under noisy observations. We report a new relationship between BTs, augmented with statistical information, and Hidden Markov Models. Exploiting this relationship will allow application of many algorithms for HMMs (and dynamic Bayesian networks) to data acquired from BT-based systems.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.10029v1
PDF	https://arxiv.org/pdf/1907.10029v1.pdf
PWC	https://paperswithcode.com/paper/hidden-markov-models-derived-from-behavior
Repo
Framework

CircConv: A Structured Convolution with Low Complexity


Title	CircConv: A Structured Convolution with Low Complexity
Authors	Siyu Liao, Zhe Li, Liang Zhao, Qinru Qiu, Yanzhi Wang, Bo Yuan
Abstract	Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation resource and weight storage, thereby limiting the practical deployment of DNNs. To overcome these limitations, this paper proposes to impose the circulant structure to the construction of convolutional layers, and hence leads to circulant convolutional layers (CircConvs) and circulant CNNs. The circulant structure and models can be either trained from scratch or re-trained from a pre-trained non-circulant model, thereby making it very flexible for different training environments. Through extensive experiments, such strong structure-imposing approach is proved to be able to substantially reduce the number of parameters of convolutional layers and enable significant saving of computational cost by using fast multiplication of the circulant tensor.
Tasks
Published	2019-02-28
URL	http://arxiv.org/abs/1902.11268v1
PDF	http://arxiv.org/pdf/1902.11268v1.pdf
PWC	https://paperswithcode.com/paper/circconv-a-structured-convolution-with-low
Repo
Framework

Image De-Noising For Salt and Pepper Noise by Introducing New Enhanced Filter


Title	Image De-Noising For Salt and Pepper Noise by Introducing New Enhanced Filter
Authors	Vivek Kumar, Atul Samadhiya
Abstract	When an image is formed, factors such as lighting (spectra, source, and intensity) and camera characteristics (sensor response, lenses) affect the appearance of the image. Therefore, the prime factor that reduces the quality of the image is noise. It hides the important details and information of images. In order to enhance the qualities of the image, the removal of noises become imperative and that should not at the cost of any loss of image information. Noise removal is one of the pre-processing stages of image processing. In this paper a new method for the enhancement of grayscale images is introduced, when images are corrupted by fixed valued impulse noise (salt and pepper noise). The proposed methodology ensures a better output for the low and medium density of fixed value impulse noise as compared to the other famous filters like Standard Median Filter (SMF), Decision Based Median Filter (DBMF) and Modified Decision Based Median Filter (MDBMF) etc. The main objective of the proposed method was to improve peak signal to noise ratio (PSNR), visual perception and reduction in the blurring of the image. The proposed algorithm replaced the noisy pixel by trimmed mean value. When previous pixel values, 0s, and 255s are present in the particular window and all the pixel values are 0s and 255s then the remaining noisy pixels are replaced by mean value. The gray-scale image of mandrill and Lena were tested via the proposed method. The experimental result shows better peak signal to noise ratio (PSNR), mean square error values with better visual and human perception.
Tasks
Published	2019-01-19
URL	http://arxiv.org/abs/1901.06528v1
PDF	http://arxiv.org/pdf/1901.06528v1.pdf
PWC	https://paperswithcode.com/paper/image-de-noising-for-salt-and-pepper-noise-by
Repo
Framework

Recovering Variable Names for Minified Code with Usage Contexts


Title	Recovering Variable Names for Minified Code with Usage Contexts
Authors	Hieu Tran, Ngoc Tran, Son Nguyen, Hoan Nguyen, Tien Nguyen
Abstract	In modern Web technology, JavaScript (JS) code plays an important role. To avoid the exposure of original source code, the variable names in JS code deployed in the wild are often replaced by short, meaningless names, thus making the code extremely difficult to manually understand and analysis. This paper presents JSNeat, an information retrieval (IR)-based approach to recover the variable names in minified JS code. JSNeat follows a data-driven approach to recover names by searching for them in a large corpus of open-source JS code. We use three types of contexts to match a variable in given minified code against the corpus including the context of properties and roles of the variable, the context of that variable and relations with other variables under recovery, and the context of the task of the function to which the variable contributes. We performed several empirical experiments to evaluate JSNeat on the dataset of more than 322K JS files with 1M functions, and 3.5M variables with 176K unique variable names. We found that JSNeat achieves a high accuracy of 69.1%, which is the relative improvements of 66.1% and 43% over two state-of-the-art approaches JSNice and JSNaughty, respectively. The time to recover for a file or for a variable with JSNeat is twice as fast as with JSNice and 4x as fast as with JNaughty, respectively.
Tasks	Information Retrieval
Published	2019-06-08
URL	https://arxiv.org/abs/1906.03488v1
PDF	https://arxiv.org/pdf/1906.03488v1.pdf
PWC	https://paperswithcode.com/paper/recovering-variable-names-for-minified-code
Repo
Framework

Defensive Escort Teams via Multi-Agent Deep Reinforcement Learning


Title	Defensive Escort Teams via Multi-Agent Deep Reinforcement Learning
Authors	Arpit Garg, Yazied A. Hasan, Adam Yañez, Lydia Tapia
Abstract	Coordinated defensive escorts can aid a navigating payload by positioning themselves in order to maintain the safety of the payload from obstacles. In this paper, we present a novel, end-to-end solution for coordinating an escort team for protecting high-value payloads. Our solution employs deep reinforcement learning (RL) in order to train a team of escorts to maintain payload safety while navigating alongside the payload. This is done in a distributed fashion, relying only on limited range positional information of other escorts, the payload, and the obstacles. When compared to a state-of-art algorithm for obstacle avoidance, our solution with a single escort increases navigation success up to 31%. Additionally, escort teams increase success rate by up to 75% percent over escorts in static formations. We also show that this learned solution is general to several adaptations in the scenario including: a changing number of escorts in the team, changing obstacle density, and changes in payload conformation. Video: https://youtu.be/SoYesKti4VA.
Tasks
Published	2019-10-09
URL	https://arxiv.org/abs/1910.04537v1
PDF	https://arxiv.org/pdf/1910.04537v1.pdf
PWC	https://paperswithcode.com/paper/defensive-escort-teams-via-multi-agent-deep
Repo
Framework

CBCT-to-CT synthesis with a single neural network for head-and-neck, lung and breast cancer adaptive radiotherapy


Title	CBCT-to-CT synthesis with a single neural network for head-and-neck, lung and breast cancer adaptive radiotherapy
Authors	Matteo Maspero, Mark HF Savenije, Tristan CF van Heijst, Joost JC Verhoeff, Alexis NTJ Kotte, Anette C Houweling, Cornelis AT van den Berg
Abstract	Purpose: CBCT-based adaptive radiotherapy requires daily images for accurate dose calculations. This study investigates the feasibility of applying a single convolutional network to facilitate CBCT-to-CT synthesis for head-and-neck, lung, and breast cancer patients. Methods: Ninety-nine patients diagnosed with head-and-neck, lung or breast cancer undergoing radiotherapy with CBCT-based position verification were included in this study. CBCTs were registered to planning CTs according to clinical procedures. Three cycle-consistent generative adversarial networks (cycle-GANs) were trained in an unpaired manner on 15 patients per anatomical site generating synthetic-CTs (sCTs). Another network was trained with all the anatomical sites together. Performances of all four networks were compared and evaluated for image similarity against rescan CT (rCT). Clinical plans were recalculated on CT and sCT and analysed through voxel-based dose differences and {\gamma}-analysis. Results: A sCT was generated in 10 seconds. Image similarity was comparable between models trained on different anatomical sites and a single model for all sites. Mean dose differences < 0.5% were obtained in high-dose regions. Mean gamma (2%,2mm) pass-rates > 95% were achieved for all sites. Conclusions: Cycle-GAN reduced CBCT artefacts and increased HU similarity to CT, enabling sCT-based dose calculations. The speed of the network can facilitate on-line adaptive radiotherapy using a single network for head-and-neck, lung and breast cancer patients.
Tasks
Published	2019-12-23
URL	https://arxiv.org/abs/1912.11136v1
PDF	https://arxiv.org/pdf/1912.11136v1.pdf
PWC	https://paperswithcode.com/paper/cbct-to-ct-synthesis-with-a-single-neural
Repo
Framework

Cycle-Consistent Adversarial GAN: the integration of adversarial attack and defense


Title	Cycle-Consistent Adversarial GAN: the integration of adversarial attack and defense
Authors	Lingyun Jiang, Kai Qiao, Ruoxi Qin, Linyuan Wang, Jian Chen, Haibing Bu, Bin Yan
Abstract	In image classification of deep learning, adversarial examples where inputs intended to add small magnitude perturbations may mislead deep neural networks (DNNs) to incorrect results, which means DNNs are vulnerable to them. Different attack and defense strategies have been proposed to better research the mechanism of deep learning. However, those research in these networks are only for one aspect, either an attack or a defense, not considering that attacks and defenses should be interdependent and mutually reinforcing, just like the relationship between spears and shields. In this paper, we propose Cycle-Consistent Adversarial GAN (CycleAdvGAN) to generate adversarial examples, which can learn and approximate the distribution of original instances and adversarial examples. For CycleAdvGAN, once the Generator and are trained, can generate adversarial perturbations efficiently for any instance, so as to make DNNs predict wrong, and recovery adversarial examples to clean instances, so as to make DNNs predict correct. We apply CycleAdvGAN under semi-white box and black-box settings on two public datasets MNIST and CIFAR10. Using the extensive experiments, we show that our method has achieved the state-of-the-art adversarial attack method and also efficiently improve the defense ability, which make the integration of adversarial attack and defense come true. In additional, it has improved attack effect only trained on the adversarial dataset generated by any kind of adversarial attack.
Tasks	Adversarial Attack, Image Classification
Published	2019-04-12
URL	http://arxiv.org/abs/1904.06026v1
PDF	http://arxiv.org/pdf/1904.06026v1.pdf
PWC	https://paperswithcode.com/paper/cycle-consistent-adversarial-gan-the
Repo
Framework

An Introduction to Quaternion-Valued Recurrent Projection Neural Networks


Title	An Introduction to Quaternion-Valued Recurrent Projection Neural Networks
Authors	Marcos Eduardo Valle, Rodolfo Anibal Lobo
Abstract	Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we introduce the quaternion-valued recurrent projection neural networks (QRPNNs). Briefly, QRPNNs are obtained by combining the non-local projection learning with the quaternion-valued recurrent correlation neural network (QRCNNs). We show that QRPNNs overcome the cross-talk problem of QRCNNs. Thus, they are appropriate to implement associative memories. Furthermore, computational experiments reveal that QRPNNs exhibit greater storage capacity and noise tolerance than their corresponding QRCNNs.
Tasks
Published	2019-09-19
URL	https://arxiv.org/abs/1909.09227v1
PDF	https://arxiv.org/pdf/1909.09227v1.pdf
PWC	https://paperswithcode.com/paper/an-introduction-to-quaternion-valued
Repo
Framework

Interpreting Context of Images using Scene Graphs


Title	Interpreting Context of Images using Scene Graphs
Authors	Himangi Mittal, Ajith Abraham, Anuja Arora
Abstract	Understanding a visual scene incorporates objects, relationships, and context. Traditional methods working on an image mostly focus on object detection and fail to capture the relationship between the objects. Relationships can give rich semantic information about the objects in a scene. The context can be conducive to comprehending an image since it will help us to perceive the relation between the objects and thus, give us a deeper insight into the image. Through this idea, our project delivers a model that focuses on finding the context present in an image by representing the image as a graph, where the nodes will the objects and edges will be the relation between them. The context is found using the visual and semantic cues which are further concatenated and given to the Support Vector Machines (SVM) to detect the relation between two objects. This presents us with the context of the image which can be further used in applications such as similar image retrieval, image captioning, or story generation.
Tasks	Image Captioning, Image Retrieval, Object Detection
Published	2019-12-01
URL	https://arxiv.org/abs/1912.00501v1
PDF	https://arxiv.org/pdf/1912.00501v1.pdf
PWC	https://paperswithcode.com/paper/interpreting-context-of-images-using-scene
Repo
Framework

A sparse negative binomial mixture model for clustering RNA-seq count data


Title	A sparse negative binomial mixture model for clustering RNA-seq count data
Authors	Tanbin Rahman, Yujia Li, Tianzhou Ma, Lu Tang, George Tseng
Abstract	Clustering with variable selection is a challenging but critical task for modern small-n-large-p data. Existing methods based on Gaussian mixture models or sparse K-means provide solutions to continuous data. With the prevalence of RNA-seq technology and lack of count data modeling for clustering, the current practice is to normalize count expression data into continuous measures and apply existing models with Gaussian assumption. In this paper, we develop a negative binomial mixture model with gene regularization to cluster samples (small $n$) with high-dimensional gene features (large $p$). EM algorithm and Bayesian information criterion are used for inference and determining tuning parameters. The method is compared with sparse Gaussian mixture model and sparse K-means using extensive simulations and two real transcriptomic applications in breast cancer and rat brain studies. The result shows superior performance of the proposed count data model in clustering accuracy, feature selection and biological interpretation by pathway enrichment analysis.
Tasks	Feature Selection
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02399v1
PDF	https://arxiv.org/pdf/1912.02399v1.pdf
PWC	https://paperswithcode.com/paper/a-sparse-negative-binomial-mixture-model-for
Repo
Framework

Yall should read this! Identifying Plurality in Second-Person Personal Pronouns in English Texts


Title	Yall should read this! Identifying Plurality in Second-Person Personal Pronouns in English Texts
Authors	Gabriel Stanovsky, Ronen Tamari
Abstract	Distinguishing between singular and plural “you” in English is a challenging task which has potential for downstream applications, such as machine translation or coreference resolution. While formal written English does not distinguish between these cases, other languages (such as Spanish), as well as other dialects of English (via phrases such as “yall”), do make this distinction. We make use of this to obtain distantly-supervised labels for the task on a large-scale in two domains. Following, we train a model to distinguish between the single/plural you, finding that although in-domain training achieves reasonable accuracy (over 77%), there is still a lot of room for improvement, especially in the domain-transfer scenario, which proves extremely challenging. Our code and data are publicly available.
Tasks	Coreference Resolution, Machine Translation
Published	2019-10-26
URL	https://arxiv.org/abs/1910.11966v1
PDF	https://arxiv.org/pdf/1910.11966v1.pdf
PWC	https://paperswithcode.com/paper/yall-should-read-this-identifying-plurality
Repo
Framework

Randomized Algorithms for Data-Driven Stabilization of Stochastic Linear Systems


Title	Randomized Algorithms for Data-Driven Stabilization of Stochastic Linear Systems
Authors	Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George Michailidis
Abstract	Data-driven control strategies for dynamical systems with unknown parameters are popular in theory and applications. An essential problem is to prevent stochastic linear systems becoming destabilized, due to the uncertainty of the decision-maker about the dynamical parameter. Two randomized algorithms are proposed for this problem, but the performance is not sufficiently investigated. Further, the effect of key parameters of the algorithms such as the magnitude and the frequency of applying the randomizations is not currently available. This work studies the stabilization speed and the failure probability of data-driven procedures. We provide numerical analyses for the performance of two methods: stochastic feedback, and stochastic parameter. The presented results imply that as long as the number of statistically independent randomizations is not too small, fast stabilization is guaranteed.
Tasks
Published	2019-05-16
URL	https://arxiv.org/abs/1905.06978v1
PDF	https://arxiv.org/pdf/1905.06978v1.pdf
PWC	https://paperswithcode.com/paper/randomized-algorithms-for-data-driven
Repo
Framework