July 28, 2019

3026 words 15 mins read

Paper Group ANR 184

Topic Modeling for Classification of Clinical Reports. Compression Fractures Detection on CT. Volume Calculation of CT lung Lesions based on Halton Low-discrepancy Sequences. Visual Semantic Planning using Deep Successor Representations. Taxonomy Induction using Hypernym Subsequences. The BURCHAK corpus: a Challenge Data Set for Interactive Learnin …

Topic Modeling for Classification of Clinical Reports


Title	Topic Modeling for Classification of Clinical Reports
Authors	Efsun Sarioglu Kayi, Kabir Yadav, James M. Chamberlain, Hyeong-Ah Choi
Abstract	Electronic health records (EHRs) contain important clinical information about patients. Efficient and effective use of this information could supplement or even replace manual chart review as a means of studying and improving the quality and safety of healthcare delivery. However, some of these clinical data are in the form of free text and require pre-processing before use in automated systems. A common free text data source is radiology reports, typically dictated by radiologists to explain their interpretations. We sought to demonstrate machine learning classification of computed tomography (CT) imaging reports into binary outcomes, i.e. positive and negative for fracture, using regular text classification and classifiers based on topic modeling. Topic modeling provides interpretable themes (topic distributions) in reports, a representation that is more compact than the commonly used bag-of-words representation and can be processed faster than raw text in subsequent automated processes. We demonstrate new classifiers based on this topic modeling representation of the reports. Aggregate topic classifier (ATC) and confidence-based topic classifier (CTC) use a single topic that is determined from the training dataset based on different measures to classify the reports on the test dataset. Alternatively, similarity-based topic classifier (STC) measures the similarity between the reports’ topic distributions to determine the predicted class. Our proposed topic modeling-based classifier systems are shown to be competitive with existing text classification techniques and provides an efficient and interpretable representation.
Tasks	Computed Tomography (CT), Text Classification
Published	2017-06-19
URL	http://arxiv.org/abs/1706.06177v1
PDF	http://arxiv.org/pdf/1706.06177v1.pdf
PWC	https://paperswithcode.com/paper/topic-modeling-for-classification-of-clinical
Repo
Framework

Compression Fractures Detection on CT


Title	Compression Fractures Detection on CT
Authors	Amir Bar, Lior Wolf, Orna Bergman Amitai, Eyal Toledano, Eldad Elnekave
Abstract	The presence of a vertebral compression fracture is highly indicative of osteoporosis and represents the single most robust predictor for development of a second osteoporotic fracture in the spine or elsewhere. Less than one third of vertebral compression fractures are diagnosed clinically. We present an automated method for detecting spine compression fractures in Computed Tomography (CT) scans. The algorithm is composed of three processes. First, the spinal column is segmented and sagittal patches are extracted. The patches are then binary classified using a Convolutional Neural Network (CNN). Finally a Recurrent Neural Network (RNN) is utilized to predict whether a vertebral fracture is present in the series of patches.
Tasks	Computed Tomography (CT)
Published	2017-06-06
URL	http://arxiv.org/abs/1706.01671v1
PDF	http://arxiv.org/pdf/1706.01671v1.pdf
PWC	https://paperswithcode.com/paper/compression-fractures-detection-on-ct
Repo
Framework

Volume Calculation of CT lung Lesions based on Halton Low-discrepancy Sequences


Title	Volume Calculation of CT lung Lesions based on Halton Low-discrepancy Sequences
Authors	Liansheng Wang, Shusheng Li, Shuo Li
Abstract	Volume calculation from the Computed Tomography (CT) lung lesions data is a significant parameter for clinical diagnosis. The volume is widely used to assess the severity of the lung nodules and track its progression, however, the accuracy and efficiency of previous studies are not well achieved for clinical uses. It remains to be a challenging task due to its tight attachment to the lung wall, inhomogeneous background noises and large variations in sizes and shape. In this paper, we employ Halton low-discrepancy sequences to calculate the volume of the lung lesions. The proposed method directly compute the volume without the procedure of three-dimension (3D) model reconstruction and surface triangulation, which significantly improves the efficiency and reduces the complexity. The main steps of the proposed method are: (1) generate a certain number of random points in each slice using Halton low-discrepancy sequences and calculate the lesion area of each slice through the proportion; (2) obtain the volume by integrating the areas in the sagittal direction. In order to evaluate our proposed method, the experiments were conducted on the sufficient data sets with different size of lung lesions. With the uniform distribution of random points, our proposed method achieves more accurate results compared with other methods, which demonstrates the robustness and accuracy for the volume calculation of CT lung lesions. In addition, our proposed method is easy to follow and can be extensively applied to other applications, e.g., volume calculation of liver tumor, atrial wall aneurysm, etc.
Tasks	Computed Tomography (CT)
Published	2017-06-06
URL	http://arxiv.org/abs/1706.01644v1
PDF	http://arxiv.org/pdf/1706.01644v1.pdf
PWC	https://paperswithcode.com/paper/volume-calculation-of-ct-lung-lesions-based
Repo
Framework

Visual Semantic Planning using Deep Successor Representations


Title	Visual Semantic Planning using Deep Successor Representations
Authors	Yuke Zhu, Daniel Gordon, Eric Kolve, Dieter Fox, Li Fei-Fei, Abhinav Gupta, Roozbeh Mottaghi, Ali Farhadi
Abstract	A crucial capability of real-world intelligent agents is their ability to plan a sequence of actions to achieve their goals in the visual world. In this work, we address the problem of visual semantic planning: the task of predicting a sequence of actions from visual observations that transform a dynamic environment from an initial state to a goal state. Doing so entails knowledge about objects and their affordances, as well as actions and their preconditions and effects. We propose learning these through interacting with a visual and dynamic environment. Our proposed solution involves bootstrapping reinforcement learning with imitation learning. To ensure cross task generalization, we develop a deep predictive model based on successor representations. Our experimental results show near optimal results across a wide range of tasks in the challenging THOR environment.
Tasks	Imitation Learning
Published	2017-05-23
URL	http://arxiv.org/abs/1705.08080v2
PDF	http://arxiv.org/pdf/1705.08080v2.pdf
PWC	https://paperswithcode.com/paper/visual-semantic-planning-using-deep-successor
Repo
Framework

Taxonomy Induction using Hypernym Subsequences


Title	Taxonomy Induction using Hypernym Subsequences
Authors	Amit Gupta, Rémi Lebret, Hamza Harkous, Karl Aberer
Abstract	We propose a novel, semi-supervised approach towards domain taxonomy induction from an input vocabulary of seed terms. Unlike all previous approaches, which typically extract direct hypernym edges for terms, our approach utilizes a novel probabilistic framework to extract hypernym subsequences. Taxonomy induction from extracted subsequences is cast as an instance of the minimumcost flow problem on a carefully designed directed graph. Through experiments, we demonstrate that our approach outperforms stateof- the-art taxonomy induction approaches across four languages. Importantly, we also show that our approach is robust to the presence of noise in the input vocabulary. To the best of our knowledge, no previous approaches have been empirically proven to manifest noise-robustness in the input vocabulary.
Tasks
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07626v4
PDF	http://arxiv.org/pdf/1704.07626v4.pdf
PWC	https://paperswithcode.com/paper/taxonomy-induction-using-hypernym
Repo
Framework

The BURCHAK corpus: a Challenge Data Set for Interactive Learning of Visually Grounded Word Meanings


Title	The BURCHAK corpus: a Challenge Data Set for Interactive Learning of Visually Grounded Word Meanings
Authors	Yanchao Yu, Arash Eshghi, Gregory Mills, Oliver Joseph Lemon
Abstract	We motivate and describe a new freely available human-human dialogue dataset for interactive learning of visually grounded word meanings through ostensive definition by a tutor to a learner. The data has been collected using a novel, character-by-character variant of the DiET chat tool (Healey et al., 2003; Mills and Healey, submitted) with a novel task, where a Learner needs to learn invented visual attribute words (such as " burchak " for square) from a tutor. As such, the text-based interactions closely resemble face-to-face conversation and thus contain many of the linguistic phenomena encountered in natural, spontaneous dialogue. These include self-and other-correction, mid-sentence continuations, interruptions, overlaps, fillers, and hedges. We also present a generic n-gram framework for building user (i.e. tutor) simulations from this type of incremental data, which is freely available to researchers. We show that the simulations produce outputs that are similar to the original data (e.g. 78% turn match similarity). Finally, we train and evaluate a Reinforcement Learning dialogue control agent for learning visually grounded word meanings, trained from the BURCHAK corpus. The learned policy shows comparable performance to a rule-based system built previously.
Tasks
Published	2017-09-29
URL	http://arxiv.org/abs/1709.10431v1
PDF	http://arxiv.org/pdf/1709.10431v1.pdf
PWC	https://paperswithcode.com/paper/the-burchak-corpus-a-challenge-data-set-for
Repo
Framework

The best defense is a good offense: Countering black box attacks by predicting slightly wrong labels


Title	The best defense is a good offense: Countering black box attacks by predicting slightly wrong labels
Authors	Yannic Kilcher, Thomas Hofmann
Abstract	Black-Box attacks on machine learning models occur when an attacker, despite having no access to the inner workings of a model, can successfully craft an attack by means of model theft. The attacker will train an own substitute model that mimics the model to be attacked. The substitute can then be used to design attacks against the original model, for example by means of adversarial samples. We put ourselves in the shoes of the defender and present a method that can successfully avoid model theft by mounting a counter-attack. Specifically, to any incoming query, we slightly perturb our output label distribution in a way that makes substitute training infeasible. We demonstrate that the perturbation does not affect the ordinary use of our model, but results in an effective defense against attacks based on model theft.
Tasks
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05475v1
PDF	http://arxiv.org/pdf/1711.05475v1.pdf
PWC	https://paperswithcode.com/paper/the-best-defense-is-a-good-offense-countering
Repo
Framework

Approximations from Anywhere and General Rough Sets


Title	Approximations from Anywhere and General Rough Sets
Authors	A. Mani
Abstract	Not all approximations arise from information systems. The problem of fitting approximations, subjected to some rules (and related data), to information systems in a rough scheme of things is known as the \emph{inverse problem}. The inverse problem is more general than the duality (or abstract representation) problems and was introduced by the present author in her earlier papers. From the practical perspective, a few (as opposed to one) theoretical frameworks may be suitable for formulating the problem itself. \emph{Granular operator spaces} have been recently introduced and investigated by the present author in her recent work in the context of antichain based and dialectical semantics for general rough sets. The nature of the inverse problem is examined from number-theoretic and combinatorial perspectives in a higher order variant of granular operator spaces and some necessary conditions are proved. The results and the novel approach would be useful in a number of unsupervised and semi supervised learning contexts and algorithms.
Tasks
Published	2017-04-18
URL	http://arxiv.org/abs/1704.05443v1
PDF	http://arxiv.org/pdf/1704.05443v1.pdf
PWC	https://paperswithcode.com/paper/approximations-from-anywhere-and-general
Repo
Framework

An Error Detection and Correction Framework for Connectomics


Title	An Error Detection and Correction Framework for Connectomics
Authors	Jonathan Zung, Ignacio Tartavull, Kisuk Lee, H. Sebastian Seung
Abstract	We define and study error detection and correction tasks that are useful for 3D reconstruction of neurons from electron microscopic imagery, and for image segmentation more generally. Both tasks take as input the raw image and a binary mask representing a candidate object. For the error detection task, the desired output is a map of split and merge errors in the object. For the error correction task, the desired output is the true object. We call this object mask pruning, because the candidate object mask is assumed to be a superset of the true object. We train multiscale 3D convolutional networks to perform both tasks. We find that the error-detecting net can achieve high accuracy. The accuracy of the error-correcting net is enhanced if its input object mask is “advice” (union of erroneous objects) from the error-detecting net.
Tasks	3D Reconstruction, Semantic Segmentation
Published	2017-08-08
URL	http://arxiv.org/abs/1708.02599v2
PDF	http://arxiv.org/pdf/1708.02599v2.pdf
PWC	https://paperswithcode.com/paper/an-error-detection-and-correction-framework
Repo
Framework

Deep Forward and Inverse Perceptual Models for Tracking and Prediction


Title	Deep Forward and Inverse Perceptual Models for Tracking and Prediction
Authors	Alexander Lambert, Amirreza Shaban, Amit Raj, Zhen Liu, Byron Boots
Abstract	We consider the problems of learning forward models that map state to high-dimensional images and inverse models that map high-dimensional images to state in robotics. Specifically, we present a perceptual model for generating video frames from state with deep networks, and provide a framework for its use in tracking and prediction tasks. We show that our proposed model greatly outperforms standard deconvolutional methods and GANs for image generation, producing clear, photo-realistic images. We also develop a convolutional neural network model for state estimation and compare the result to an Extended Kalman Filter to estimate robot trajectories. We validate all models on a real robotic system.
Tasks	Image Generation
Published	2017-10-31
URL	http://arxiv.org/abs/1710.11311v2
PDF	http://arxiv.org/pdf/1710.11311v2.pdf
PWC	https://paperswithcode.com/paper/deep-forward-and-inverse-perceptual-models
Repo
Framework

Look Wider to Match Image Patches with Convolutional Neural Networks


Title	Look Wider to Match Image Patches with Convolutional Neural Networks
Authors	Haesol Park, Kyoung Mu Lee
Abstract	When a human matches two images, the viewer has a natural tendency to view the wide area around the target pixel to obtain clues of right correspondence. However, designing a matching cost function that works on a large window in the same way is difficult. The cost function is typically not intelligent enough to discard the information irrelevant to the target pixel, resulting in undesirable artifacts. In this paper, we propose a novel learn a stereo matching cost with a large-sized window. Unlike conventional pooling layers with strides, the proposed per-pixel pyramid-pooling layer can cover a large area without a loss of resolution and detail. Therefore, the learned matching cost function can successfully utilize the information from a large area without introducing the fattening effect. The proposed method is robust despite the presence of weak textures, depth discontinuity, illumination, and exposure difference. The proposed method achieves near-peak performance on the Middlebury benchmark.
Tasks	Stereo Matching, Stereo Matching Hand
Published	2017-09-19
URL	http://arxiv.org/abs/1709.06248v1
PDF	http://arxiv.org/pdf/1709.06248v1.pdf
PWC	https://paperswithcode.com/paper/look-wider-to-match-image-patches-with
Repo
Framework

Gaussian Lower Bound for the Information Bottleneck Limit


Title	Gaussian Lower Bound for the Information Bottleneck Limit
Authors	Amichai Painsky, Naftali Tishby
Abstract	The Information Bottleneck (IB) is a conceptual method for extracting the most compact, yet informative, representation of a set of variables, with respect to the target. It generalizes the notion of minimal sufficient statistics from classical parametric statistics to a broader information-theoretic sense. The IB curve defines the optimal trade-off between representation complexity and its predictive power. Specifically, it is achieved by minimizing the level of mutual information (MI) between the representation and the original variables, subject to a minimal level of MI between the representation and the target. This problem is shown to be in general NP hard. One important exception is the multivariate Gaussian case, for which the Gaussian IB (GIB) is known to obtain an analytical closed form solution, similar to Canonical Correlation Analysis (CCA). In this work we introduce a Gaussian lower bound to the IB curve; we find an embedding of the data which maximizes its “Gaussian part”, on which we apply the GIB. This embedding provides an efficient (and practical) representation of any arbitrary data-set (in the IB sense), which in addition holds the favorable properties of a Gaussian distribution. Importantly, we show that the optimal Gaussian embedding is bounded from above by non-linear CCA. This allows a fundamental limit for our ability to Gaussianize arbitrary data-sets and solve complex problems by linear methods.
Tasks
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02421v1
PDF	http://arxiv.org/pdf/1711.02421v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-lower-bound-for-the-information
Repo
Framework

Objects as context for detecting their semantic parts


Title	Objects as context for detecting their semantic parts
Authors	Abel Gonzalez-Garcia, Davide Modolo, Vittorio Ferrari
Abstract	We present a semantic part detection approach that effectively leverages object information.We use the object appearance and its class as indicators of what parts to expect. We also model the expected relative location of parts inside the objects based on their appearance. We achieve this with a new network module, called OffsetNet, that efficiently predicts a variable number of part locations within a given object. Our model incorporates all these cues to detect parts in the context of their objects. This leads to considerably higher performance for the challenging task of part detection compared to using part appearance alone (+5 mAP on the PASCAL-Part dataset). We also compare to other part detection methods on both PASCAL-Part and CUB200-2011 datasets.
Tasks
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09529v3
PDF	http://arxiv.org/pdf/1703.09529v3.pdf
PWC	https://paperswithcode.com/paper/objects-as-context-for-detecting-their
Repo
Framework

Video Object Segmentation using Supervoxel-Based Gerrymandering


Title	Video Object Segmentation using Supervoxel-Based Gerrymandering
Authors	Brent A. Griffin, Jason J. Corso
Abstract	Pixels operate locally. Superpixels have some potential to collect information across many pixels; supervoxels have more potential by implicitly operating across time. In this paper, we explore this well established notion thoroughly analyzing how supervoxels can be used in place of and in conjunction with other means of aggregating information across space-time. Focusing on the problem of strictly unsupervised video object segmentation, we devise a method called supervoxel gerrymandering that links masks of foregroundness and backgroundness via local and non-local consensus measures. We pose and answer a series of critical questions about the ability of supervoxels to adequately sway local voting; the questions regard type and scale of supervoxels as well as local versus non-local consensus, and the questions are posed in a general way so as to impact the broader knowledge of the use of supervoxels in video understanding. We work with the DAVIS dataset and find that our analysis yields an unsupervised method that outperforms all other known unsupervised methods and even many supervised ones.
Tasks	Semantic Segmentation, Unsupervised Video Object Segmentation, Video Object Segmentation, Video Semantic Segmentation, Video Understanding
Published	2017-04-18
URL	http://arxiv.org/abs/1704.05165v1
PDF	http://arxiv.org/pdf/1704.05165v1.pdf
PWC	https://paperswithcode.com/paper/video-object-segmentation-using-supervoxel
Repo
Framework

Convolutional neural networks that teach microscopes how to image


Title	Convolutional neural networks that teach microscopes how to image
Authors	Roarke Horstmeyer, Richard Y. Chen, Barbara Kappes, Benjamin Judkewitz
Abstract	Deep learning algorithms offer a powerful means to automatically analyze the content of medical images. However, many biological samples of interest are primarily transparent to visible light and contain features that are difficult to resolve with a standard optical microscope. Here, we use a convolutional neural network (CNN) not only to classify images, but also to optimize the physical layout of the imaging device itself. We increase the classification accuracy of a microscope’s recorded images by merging an optical model of image formation into the pipeline of a CNN. The resulting network simultaneously determines an ideal illumination arrangement to highlight important sample features during image acquisition, along with a set of convolutional weights to classify the detected images post-capture. We demonstrate our joint optimization technique with an experimental microscope configuration that automatically identifies malaria-infected cells with 5-10% higher accuracy than standard and alternative microscope lighting designs.
Tasks
Published	2017-09-21
URL	http://arxiv.org/abs/1709.07223v1
PDF	http://arxiv.org/pdf/1709.07223v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-that-teach
Repo
Framework