January 25, 2020

3246 words 16 mins read

Paper Group ANR 1706

Bernoulli Race Particle Filters. Multiple Causes: A Causal Graphical View. Robust Unsupervised Flexible Auto-weighted Local-Coordinate Concept Factorization for Image Clustering. Generalizing Psychological Similarity Spaces to Unseen Stimuli. Extending a model for ontology-based Arabic-English machine translation. Correlation Maximized Structural S …

Bernoulli Race Particle Filters


Title	Bernoulli Race Particle Filters
Authors	Sebastian M Schmon, Arnaud Doucet, George Deligiannidis
Abstract	When the weights in a particle filter are not available analytically, standard resampling methods cannot be employed. To circumvent this problem state-of-the-art algorithms replace the true weights with non-negative unbiased estimates. This algorithm is still valid but at the cost of higher variance of the resulting filtering estimates in comparison to a particle filter using the true weights. We propose here a novel algorithm that allows for resampling according to the true intractable weights when only an unbiased estimator of the weights is available. We demonstrate our algorithm on several examples.
Tasks
Published	2019-03-03
URL	http://arxiv.org/abs/1903.00939v1
PDF	http://arxiv.org/pdf/1903.00939v1.pdf
PWC	https://paperswithcode.com/paper/bernoulli-race-particle-filters
Repo
Framework

Multiple Causes: A Causal Graphical View


Title	Multiple Causes: A Causal Graphical View
Authors	Yixin Wang, David M. Blei
Abstract	Unobserved confounding is a major hurdle for causal inference from observational data. Confounders—the variables that affect both the causes and the outcome—induce spurious non-causal correlations between the two. Wang & Blei (2018) lower this hurdle with “the blessings of multiple causes,” where the correlation structure of multiple causes provides indirect evidence for unobserved confounding. They leverage these blessings with an algorithm, called the deconfounder, that uses probabilistic factor models to correct for the confounders. In this paper, we take a causal graphical view of the deconfounder. In a graph that encodes shared confounding, we show how the multiplicity of causes can help identify intervention distributions. We then justify the deconfounder, showing that it makes valid inferences of the intervention. Finally, we expand the class of graphs, and its theory, to those that include other confounders and selection variables. Our results expand the theory in Wang & Blei (2018), justify the deconfounder for causal graphs, and extend the settings where it can be used.
Tasks	Causal Inference
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12793v1
PDF	https://arxiv.org/pdf/1905.12793v1.pdf
PWC	https://paperswithcode.com/paper/multiple-causes-a-causal-graphical-view
Repo
Framework

Robust Unsupervised Flexible Auto-weighted Local-Coordinate Concept Factorization for Image Clustering


Title	Robust Unsupervised Flexible Auto-weighted Local-Coordinate Concept Factorization for Image Clustering
Authors	Zhao Zhang, Yan Zhang, Sheng Li, Guangcan Liu, Meng Wang, Shuicheng Yan
Abstract	We investigate the high-dimensional data clustering problem by proposing a novel and unsupervised representation learning model called Robust Flexible Auto-weighted Local-coordinate Concept Factorization (RFA-LCF). RFA-LCF integrates the robust flexible CF, robust sparse local-coordinate coding and the adaptive reconstruction weighting learning into a unified model. The adaptive weighting is driven by including the joint manifold preserving constraints on the recovered clean data, basis concepts and new representation. Specifically, our RFA-LCF uses a L2,1-norm based flexible residue to encode the mismatch between clean data and its reconstruction, and also applies the robust adaptive sparse local-coordinate coding to represent the data using a few nearby basis concepts, which can make the factorization more accurate and robust to noise. The robust flexible factorization is also performed in the recovered clean data space for enhancing representations. RFA-LCF also considers preserving the local manifold structures of clean data space, basis concept space and the new coordinate space jointly in an adaptive manner way. Extensive comparisons show that RFA-LCF can deliver enhanced clustering results.
Tasks	Image Clustering, Representation Learning, Unsupervised Representation Learning
Published	2019-05-25
URL	https://arxiv.org/abs/1905.10564v1
PDF	https://arxiv.org/pdf/1905.10564v1.pdf
PWC	https://paperswithcode.com/paper/robust-unsupervised-flexible-auto-weighted
Repo
Framework

Generalizing Psychological Similarity Spaces to Unseen Stimuli


Title	Generalizing Psychological Similarity Spaces to Unseen Stimuli
Authors	Lucas Bechberger, Kai-Uwe Kühnberger
Abstract	The cognitive framework of conceptual spaces proposes to represent concepts as regions in psychological similarity spaces. These similarity spaces are typically obtained through multidimensional scaling (MDS), which converts human dissimilarity ratings for a fixed set of stimuli into a spatial representation. One can distinguish metric MDS (which assumes that the dissimilarity ratings are interval or ratio scaled) from nonmetric MDS (which only assumes an ordinal scale). In our first study, we show that despite its additional assumptions, metric MDS does not necessarily yield better solutions than nonmetric MDS. In this chapter, we furthermore propose to learn a mapping from raw stimuli into the similarity space using artificial neural networks (ANNs) in order to generalize the similarity space to unseen inputs. In our second study, we show that a linear regression from the activation vectors of a convolutional ANN to similarity spaces obtained by MDS can be successful and that the results are sensitive to the number of dimensions of the similarity space.
Tasks
Published	2019-08-25
URL	https://arxiv.org/abs/1908.09260v1
PDF	https://arxiv.org/pdf/1908.09260v1.pdf
PWC	https://paperswithcode.com/paper/generalizing-psychological-similarity-spaces
Repo
Framework

Extending a model for ontology-based Arabic-English machine translation


Title	Extending a model for ontology-based Arabic-English machine translation
Authors	Neama Abdulaziz Dahan, Fadl Mutaher Ba-Alwi
Abstract	The acceleration in telecommunication needs leads to many groups of research, especially in communication facilitating and Machine Translation fields. While people contact with others having different languages and cultures, they need to have instant translations. However, the available instant translators are still providing somewhat bad Arabic-English Translations, for instance when translating books or articles, the meaning is not totally accurate. Therefore, using the semantic web techniques to deal with the homographs and homonyms semantically, the aim of this research is to extend a model for the ontology-based Arabic-English Machine Translation, named NAN, which simulate the human way in translation. The experimental results show that NAN translation is approximately more similar to the Human Translation than the other instant translators. The resulted translation will help getting the translated texts in the target language somewhat correctly and semantically more similar to human translations for the Non-Arabic Natives and the Non-English natives.
Tasks	Machine Translation
Published	2019-02-06
URL	http://arxiv.org/abs/1902.02326v1
PDF	http://arxiv.org/pdf/1902.02326v1.pdf
PWC	https://paperswithcode.com/paper/extending-a-model-for-ontology-based-arabic
Repo
Framework

Correlation Maximized Structural Similarity Loss for Semantic Segmentation


Title	Correlation Maximized Structural Similarity Loss for Semantic Segmentation
Authors	Shuai Zhao, Boxi Wu, Wenqing Chu, Yao Hu, Deng Cai
Abstract	Most semantic segmentation models treat semantic segmentation as a pixel-wise classification task and use a pixel-wise classification error as their optimization criterions. However, the pixel-wise error ignores the strong dependencies among the pixels in an image, which limits the performance of the model. Several ways to incorporate the structure information of the objects have been investigated, \eg, conditional random fields (CRF), image structure priors based methods, and generative adversarial network (GAN). Nevertheless, these methods usually require extra model branches or additional memories, and some of them show limited improvements. In contrast, we propose a simple yet effective structural similarity loss (SSL) to encode the structure information of the objects, which only requires a few additional computational resources in the training phase. Inspired by the widely-used structural similarity (SSIM) index in image quality assessment, we use the linear correlation between two images to quantify their structural similarity. And the goal of the proposed SSL is to pay more attention to the positions, whose associated predictions lead to a low degree of linear correlation between two corresponding regions in the ground truth map and the predicted map. Thus the model can achieve a strong structural similarity between the two maps through minimizing the SSL over the whole map. The experimental results demonstrate that our method can achieve substantial and consistent improvements in performance on the PASCAL VOC 2012 and Cityscapes datasets. The code will be released soon.
Tasks	Image Quality Assessment, Semantic Segmentation
Published	2019-10-19
URL	https://arxiv.org/abs/1910.08711v1
PDF	https://arxiv.org/pdf/1910.08711v1.pdf
PWC	https://paperswithcode.com/paper/correlation-maximized-structural-similarity
Repo
Framework

Deep Hashing Learning for Visual and Semantic Retrieval of Remote Sensing Images


Title	Deep Hashing Learning for Visual and Semantic Retrieval of Remote Sensing Images
Authors	Weiwei Song, Shutao Li, Jon Atli Benediktsson
Abstract	Driven by the urgent demand for managing remote sensing big data, large-scale remote sensing image retrieval (RSIR) attracts increasing attention in the remote sensing field. In general, existing retrieval methods can be regarded as visual-based retrieval approaches which search and return a set of similar images from a database to a given query image. Although retrieval methods have achieved great success, there is still a question that needs to be responded to: Can we obtain the accurate semantic labels of the returned similar images to further help analyzing and processing imagery? Inspired by the above question, in this paper, we redefine the image retrieval problem as visual and semantic retrieval of images. Specifically, we propose a novel deep hashing convolutional neural network (DHCNN) to simultaneously retrieve the similar images and classify their semantic labels in a unified framework. In more detail, a convolutional neural network (CNN) is used to extract high-dimensional deep features. Then, a hash layer is perfectly inserted into the network to transfer the deep features into compact hash codes. In addition, a fully connected layer with a softmax function is performed on hash layer to generate class distribution. Finally, a loss function is elaborately designed to simultaneously consider the label loss of each image and similarity loss of pairs of images. Experimental results on two remote sensing datasets demonstrate that the proposed method achieves the state-of-art retrieval and classification performance.
Tasks	Image Retrieval
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04614v1
PDF	https://arxiv.org/pdf/1909.04614v1.pdf
PWC	https://paperswithcode.com/paper/deep-hashing-learning-for-visual-and-semantic
Repo
Framework

Predicting Clinical Outcome of Stroke Patients with Tractographic Feature


Title	Predicting Clinical Outcome of Stroke Patients with Tractographic Feature
Authors	Po-Yu Kao, Jefferson W. Chen, B. S. Manjunath
Abstract	The volume of stroke lesion is the gold standard for predicting the clinical outcome of stroke patients. However, the presence of stroke lesion may cause neural disruptions to other brain regions, and these potentially damaged regions may affect the clinical outcome of stroke patients. In this paper, we introduce the tractographic feature to capture these potentially damaged regions and predict the modified Rankin Scale (mRS), which is a widely used outcome measure in stroke clinical trials. The tractographic feature is built from the stroke lesion and average connectome information from a group of normal subjects. The tractographic feature takes into account different functional regions that may be affected by the stroke, thus complementing the commonly used stroke volume features. The proposed tractographic feature is tested on a public stroke benchmark Ischemic Stroke Lesion Segmentation 2017 and achieves higher accuracy than the stroke volume and the state-of-the-art feature on predicting the mRS grades of stroke patients. In addition, the tractographic feature also yields a lower average absolute error than the commonly used stroke volume feature.
Tasks	Ischemic Stroke Lesion Segmentation, Lesion Segmentation
Published	2019-07-22
URL	https://arxiv.org/abs/1907.10419v3
PDF	https://arxiv.org/pdf/1907.10419v3.pdf
PWC	https://paperswithcode.com/paper/predicting-clinical-outcome-of-stroke
Repo
Framework

A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization


Title	A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization
Authors	Yucheng Chen, Matus Telgarsky, Chao Zhang, Bolton Bailey, Daniel Hsu, Jian Peng
Abstract	This paper provides a simple procedure to fit generative networks to target distributions, with the goal of a small Wasserstein distance (or other optimal transport costs). The approach is based on two principles: (a) if the source randomness of the network is a continuous distribution (the “semi-discrete” setting), then the Wasserstein distance is realized by a deterministic optimal transport mapping; (b) given an optimal transport mapping between a generator network and a target distribution, the Wasserstein distance may be decreased via a regression between the generated data and the mapped target points. The procedure here therefore alternates these two steps, forming an optimal transport and regressing against it, gradually adjusting the generator network towards the target distribution. Mathematically, this approach is shown to minimize the Wasserstein distance to both the empirical target distribution, and also its underlying population counterpart. Empirically, good performance is demonstrated on the training and testing sets of the MNIST and Thin-8 data. The paper closes with a discussion of the unsuitability of the Wasserstein distance for certain tasks, as has been identified in prior work [Arora et al., 2017, Huang et al., 2017].
Tasks
Published	2019-06-08
URL	https://arxiv.org/abs/1906.03471v2
PDF	https://arxiv.org/pdf/1906.03471v2.pdf
PWC	https://paperswithcode.com/paper/a-gradual-semi-discrete-approach-to
Repo
Framework

Fast and Reliable Architecture Selection for Convolutional Neural Networks


Title	Fast and Reliable Architecture Selection for Convolutional Neural Networks
Authors	Lukas Hahn, Lutz Roese-Koerner, Klaus Friedrichs, Anton Kummert
Abstract	The performance of a Convolutional Neural Network (CNN) depends on its hyperparameters, like the number of layers, kernel sizes, or the learning rate for example. Especially in smaller networks and applications with limited computational resources, optimisation is key. We present a fast and efficient approach for CNN architecture selection. Taking into account time consumption, precision and robustness, we develop a heuristic to quickly and reliably assess a network’s performance. In combination with Bayesian optimisation (BO), to effectively cover the vast parameter space, our contribution offers a plain and powerful architecture search for this machine learning technique.
Tasks	Bayesian Optimisation, Neural Architecture Search
Published	2019-05-06
URL	https://arxiv.org/abs/1905.01924v1
PDF	https://arxiv.org/pdf/1905.01924v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-reliable-architecture-selection-for
Repo
Framework

Seq-SG2SL: Inferring Semantic Layout from Scene Graph Through Sequence to Sequence Learning


Title	Seq-SG2SL: Inferring Semantic Layout from Scene Graph Through Sequence to Sequence Learning
Authors	Boren Li, Boyu Zhuang, Mingyang Li, Jian Gu
Abstract	Generating semantic layout from scene graph is a crucial intermediate task connecting text to image. We present a conceptually simple, flexible and general framework using sequence to sequence (seq-to-seq) learning for this task. The framework, called Seq-SG2SL, derives sequence proxies for the two modality and a Transformer-based seq-to-seq model learns to transduce one into the other. A scene graph is decomposed into a sequence of semantic fragments (SF), one for each relationship. A semantic layout is represented as the consequence from a series of brick-action code segments (BACS), dictating the position and scale of each object bounding box in the layout. Viewing the two building blocks, SF and BACS, as corresponding terms in two different vocabularies, a seq-to-seq model is fittingly used to translate. A new metric, semantic layout evaluation understudy (SLEU), is devised to evaluate the task of semantic layout prediction inspired by BLEU. SLEU defines relationships within a layout as unigrams and looks at the spatial distribution for n-grams. Unlike the binary precision of BLEU, SLEU allows for some tolerances spatially through thresholding the Jaccard Index and is consequently more adapted to the task. Experimental results on the challenging Visual Genome dataset show improvement over a non-sequential approach based on graph convolution.
Tasks
Published	2019-08-19
URL	https://arxiv.org/abs/1908.06592v1
PDF	https://arxiv.org/pdf/1908.06592v1.pdf
PWC	https://paperswithcode.com/paper/seq-sg2sl-inferring-semantic-layout-from
Repo
Framework

Behavior Identification and Prediction for a Probabilistic Risk Framework


Title	Behavior Identification and Prediction for a Probabilistic Risk Framework
Authors	Jasprit Singh Gill, Pierluigi Pisu, Venkat N. Krovi, Matthias J. Schmid
Abstract	Operation in a real world traffic requires autonomous vehicles to be able to plan their motion in complex environments (multiple moving participants). Planning through such environment requires the right search space to be provided for the trajectory or maneuver planners so that the safest motion for the ego vehicle can be identified. Given the current states of the environment and its participants, analyzing the risks based on the predicted trajectories of all the traffic participants provides the necessary search space for the planning of motion. This paper provides a fresh taxonomy of safety / risks that an autonomous vehicle should be able to handle while navigating through traffic. It provides a reference system architecture that needs to be implemented as well as describes a novel way of identifying and predicting the behaviors of the traffic participants using classic Multi Model Adaptive Estimation (MMAE). Preliminary simulation results of the implemented model are included.
Tasks	Autonomous Vehicles
Published	2019-05-20
URL	https://arxiv.org/abs/1905.08332v1
PDF	https://arxiv.org/pdf/1905.08332v1.pdf
PWC	https://paperswithcode.com/paper/behavior-identification-and-prediction-for-a
Repo
Framework

Learning a Deep ConvNet for Multi-label Classification with Partial Labels


Title	Learning a Deep ConvNet for Multi-label Classification with Partial Labels
Authors	Thibaut Durand, Nazanin Mehrasa, Greg Mori
Abstract	Deep ConvNets have shown great performance for single-label image classification (e.g. ImageNet), but it is necessary to move beyond the single-label classification task because pictures of everyday life are inherently multi-label. Multi-label classification is a more difficult task than single-label classification because both the input images and output label spaces are more complex. Furthermore, collecting clean multi-label annotations is more difficult to scale-up than single-label annotations. To reduce the annotation cost, we propose to train a model with partial labels i.e. only some labels are known per image. We first empirically compare different labeling strategies to show the potential for using partial labels on multi-label datasets. Then to learn with partial labels, we introduce a new classification loss that exploits the proportion of known labels per example. Our approach allows the use of the same training settings as when learning with all the annotations. We further explore several curriculum learning based strategies to predict missing labels. Experiments are performed on three large-scale multi-label datasets: MS COCO, NUS-WIDE and Open Images.
Tasks	Image Classification, Multi-Label Classification
Published	2019-02-26
URL	http://arxiv.org/abs/1902.09720v1
PDF	http://arxiv.org/pdf/1902.09720v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-deep-convnet-for-multi-label
Repo
Framework

A Novel Pixel-Averaging Technique for Extracting Training Data from a Single Image, Used in ML-Based Image Enlargement


Title	A Novel Pixel-Averaging Technique for Extracting Training Data from a Single Image, Used in ML-Based Image Enlargement
Authors	Amir Rastar
Abstract	Size of the training dataset is an important factor in the performance of a machine learning algorithms and tools used in medical image processing are not exceptions. Machine learning tools normally require a decent amount of training data before they could efficiently predict a target. For image processing and computer vision, the number of images determines the validity and reliability of the training set. Medical images in some cases, suffer from poor quality and inadequate quantity required for a suitable training set. The proposed algorithm in this research obviates the need for large or even small image datasets used in machine learning based image enlargement techniques by extracting the required data from a single image. The extracted data was then introduced to a decision tree regressor for upscaling greyscale medical images at different zoom levels. Results from the algorithm are relatively acceptable compared to third-party applications and promising for future research. This technique could be tailored to the requirements of other machine learning tools and the results may be improved by further tweaking of the tools hyperparameters.
Tasks
Published	2019-03-25
URL	http://arxiv.org/abs/1904.00747v1
PDF	http://arxiv.org/pdf/1904.00747v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-pixel-averaging-technique-for
Repo
Framework

Obesity Prediction with EHR Data: A deep learning approach with interpretable elements


Title	Obesity Prediction with EHR Data: A deep learning approach with interpretable elements
Authors	Mehak Gupta, Thao-Ly T. Phan, Timothy Bunnell, Rahmatollah Beheshti
Abstract	Childhood obesity is a major public health challenge. Obesity in early childhood and adolescence can lead to obesity and other health problems in adulthood. Early prediction and identification of the children at a high risk of developing childhood obesity may help in engaging earlier and more effective interventions to prevent and manage this and other related health conditions. Existing predictive tools designed for childhood obesity primarily rely on traditional regression-type methods without exploiting longitudinal patterns of children’s data (ignoring data temporality). In this paper, we present a machine learning model specifically designed for predicting future obesity patterns from generally available items on children’s medical history. To do this, we have used a large unaugmented EHR (Electronic Health Record) dataset from a major pediatric health system in the US. We adopt a general LSTM (long short-term memory) network architecture for our model for training over dynamic (sequential) and static (demographic) EHR data. We have additionally included a set embedding and attention layers to compute the feature ranking of each timestamp and attention scores of each hidden layer corresponding to each input timestamp. These feature ranking and attention scores added interpretability at both the features and the timestamp-level.
Tasks
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02655v4
PDF	https://arxiv.org/pdf/1912.02655v4.pdf
PWC	https://paperswithcode.com/paper/an-interpretable-prediction-model-for-obesity
Repo
Framework