October 16, 2019

3060 words 15 mins read

Paper Group ANR 1072

Deep Probabilistic Ensembles: Approximate Variational Inference through KL Regularization. Simultaneous Localization And Mapping with depth Prediction using Capsule Networks for UAVs. Coconditional Autoencoding Adversarial Networks for Chinese Font Feature Learning. Evaluation of Object Trackers in Distorted Surveillance Videos. Short-Term Meaning …

Deep Probabilistic Ensembles: Approximate Variational Inference through KL Regularization


Title	Deep Probabilistic Ensembles: Approximate Variational Inference through KL Regularization
Authors	Kashyap Chitta, Jose M. Alvarez, Adam Lesnikowski
Abstract	In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scalable technique that uses a regularized ensemble to approximate a deep Bayesian Neural Network (BNN). We do so by incorporating a KL divergence penalty term into the training objective of an ensemble, derived from the evidence lower bound used in variational inference. We evaluate the uncertainty estimates obtained from our models for active learning on visual classification. Our approach steadily improves upon active learning baselines as the annotation budget is increased.
Tasks	Active Learning
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02640v2
PDF	http://arxiv.org/pdf/1811.02640v2.pdf
PWC	https://paperswithcode.com/paper/deep-probabilistic-ensembles-approximate
Repo
Framework

Simultaneous Localization And Mapping with depth Prediction using Capsule Networks for UAVs


Title	Simultaneous Localization And Mapping with depth Prediction using Capsule Networks for UAVs
Authors	Sunil Prakash, Gaelan Gu
Abstract	In this paper, we propose an novel implementation of a simultaneous localization and mapping (SLAM) system based on a monocular camera from an unmanned aerial vehicle (UAV) using Depth prediction performed with Capsule Networks (CapsNet), which possess improvements over the drawbacks of the more widely-used Convolutional Neural Networks (CNN). An Extended Kalman Filter will assist in estimating the position of the UAV so that we are able to update the belief for the environment. Results will be evaluated on a benchmark dataset to portray the accuracy of our intended approach.
Tasks	Depth Estimation, Simultaneous Localization and Mapping
Published	2018-08-16
URL	http://arxiv.org/abs/1808.05336v1
PDF	http://arxiv.org/pdf/1808.05336v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-localization-and-mapping-with
Repo
Framework

Coconditional Autoencoding Adversarial Networks for Chinese Font Feature Learning


Title	Coconditional Autoencoding Adversarial Networks for Chinese Font Feature Learning
Authors	Zhizhan Zheng, Feiyun Zhang
Abstract	In this work, we propose a novel framework named Coconditional Autoencoding Adversarial Networks (CocoAAN) for Chinese font learning, which jointly learns a generation network and two encoding networks of different feature domains using an adversarial process. The encoding networks map the glyph images into style and content features respectively via the pairwise substitution optimization strategy, and the generation network maps these two kinds of features to glyph samples. Together with a discriminative network conditioned on the extracted features, our framework succeeds in producing realistic-looking Chinese glyph images flexibly. Unlike previous models relying on the complex segmentation of Chinese components or strokes, our model can “parse” structures in an unsupervised way, through which the content feature representation of each character is captured. Experiments demonstrate our framework has a powerful generalization capacity to other unseen fonts and characters.
Tasks
Published	2018-12-11
URL	http://arxiv.org/abs/1812.04451v2
PDF	http://arxiv.org/pdf/1812.04451v2.pdf
PWC	https://paperswithcode.com/paper/coconditional-autoencoding-adversarial
Repo
Framework

Evaluation of Object Trackers in Distorted Surveillance Videos


Title	Evaluation of Object Trackers in Distorted Surveillance Videos
Authors	Roger Gomez Nieto, H. D. Benitez-Restrepo, Ivan Mauricio Cabezas
Abstract	Object tracking in realistic scenarios is a difficult problem affected by various image factors such as occlusion, clutter, confusion, object shape, unstable speed, and zooming. While these conditions do affect tracking performance, there is no clear distinction between the scene dependent challenges like occlusion, clutter, etc., and the challenges imposed by traditional notions of impairments from capture, compression, processing, and transmission. This paper is concerned with the latter interpretation of quality as it affects video tracking performance. In this work we aim to evaluate two state-of-the-art trackers (STRUCK and TLD) systematically and experimentally in surveillance videos affected by in-capture distortions such as under-exposure and defocus. We evaluate these trackers with the area under curve (AUC) values of success plots and precision curves. In spite of the fact that STRUCK and TLD have ranked high in video tracking surveys. This study concludes that incapture distortions severely affect the performance of these trackers. For this reason, the design and construction of a robust tracker with respect to these distortions remains an open question that can be answered by creating algorithms that makes use of perceptual features to compensate the degradations provided by these distortions.
Tasks	Object Tracking
Published	2018-04-04
URL	http://arxiv.org/abs/1804.01624v1
PDF	http://arxiv.org/pdf/1804.01624v1.pdf
PWC	https://paperswithcode.com/paper/evaluation-of-object-trackers-in-distorted
Repo
Framework

Short-Term Meaning Shift: A Distributional Exploration


Title	Short-Term Meaning Shift: A Distributional Exploration
Authors	Marco Del Tredici, Raquel Fernández, Gemma Boleda
Abstract	We present the first exploration of meaning shift over short periods of time in online communities using distributional representations. We create a small annotated dataset and use it to assess the performance of a standard model for meaning shift detection on short-term meaning shift. We find that the model has problems distinguishing meaning shift from referential phenomena, and propose a measure of contextual variability to remedy this.
Tasks
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03169v3
PDF	http://arxiv.org/pdf/1809.03169v3.pdf
PWC	https://paperswithcode.com/paper/short-term-meaning-shift-an-exploratory
Repo
Framework

Learning Simple Thresholded Features with Sparse Support Recovery


Title	Learning Simple Thresholded Features with Sparse Support Recovery
Authors	Hongyu Xu, Zhangyang Wang, Haichuan Yang, Ding Liu, Ji Liu
Abstract	The thresholded feature has recently emerged as an extremely efficient, yet rough empirical approximation, of the time-consuming sparse coding inference process. Such an approximation has not yet been rigorously examined, and standard dictionaries often lead to non-optimal performance when used for computing thresholded features. In this paper, we first present two theoretical recovery guarantees for the thresholded feature to exactly recover the nonzero support of the sparse code. Motivated by them, we then formulate the Dictionary Learning for Thresholded Features (DLTF) model, which learns an optimized dictionary for applying the thresholded feature. In particular, for the $(k, 2)$ norm involved, a novel proximal operator with log-linear time complexity $O(m\log m)$ is derived. We evaluate the performance of DLTF on a vast range of synthetic and real-data tasks, where DLTF demonstrates remarkable efficiency, effectiveness and robustness in all experiments. In addition, we briefly discuss the potential link between DLTF and deep learning building blocks.
Tasks	Dictionary Learning
Published	2018-04-16
URL	http://arxiv.org/abs/1804.05515v2
PDF	http://arxiv.org/pdf/1804.05515v2.pdf
PWC	https://paperswithcode.com/paper/learning-simple-thresholded-features-with
Repo
Framework

Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data


Title	Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data
Authors	Puyudi Yang, Jianbo Chen, Cho-Jui Hsieh, Jane-Ling Wang, Michael I. Jordan
Abstract	We present a probabilistic framework for studying adversarial attacks on discrete data. Based on this framework, we derive a perturbation-based method, Greedy Attack, and a scalable learning-based method, Gumbel Attack, that illustrate various tradeoffs in the design of attacks. We demonstrate the effectiveness of these methods using both quantitative metrics and human evaluation on various state-of-the-art models for text classification, including a word-based CNN, a character-based CNN and an LSTM. As as example of our results, we show that the accuracy of character-based convolutional networks drops to the level of random selection by modifying only five characters through Greedy Attack.
Tasks	Text Classification
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12316v1
PDF	http://arxiv.org/pdf/1805.12316v1.pdf
PWC	https://paperswithcode.com/paper/greedy-attack-and-gumbel-attack-generating
Repo
Framework

Understanding Deep Neural Networks through Input Uncertainties


Title	Understanding Deep Neural Networks through Input Uncertainties
Authors	Jayaraman J. Thiagarajan, Irene Kim, Rushil Anirudh, Peer-Timo Bremer
Abstract	Techniques for understanding the functioning of complex machine learning models are becoming increasingly popular, not only to improve the validation process, but also to extract new insights about the data via exploratory analysis. Though a large class of such tools currently exists, most assume that predictions are point estimates and use a sensitivity analysis of these estimates to interpret the model. Using lightweight probabilistic networks we show how including prediction uncertainties in the sensitivity analysis leads to: (i) more robust and generalizable models; and (ii) a new approach for model interpretation through uncertainty decomposition. In particular, we introduce a new regularization that takes both the mean and variance of a prediction into account and demonstrate that the resulting networks provide improved generalization to unseen data. Furthermore, we propose a new technique to explain prediction uncertainties through uncertainties in the input domain, thus providing new ways to validate and interpret deep learning models.
Tasks
Published	2018-10-31
URL	http://arxiv.org/abs/1810.13425v2
PDF	http://arxiv.org/pdf/1810.13425v2.pdf
PWC	https://paperswithcode.com/paper/understanding-deep-neural-networks-through
Repo
Framework

Behavioural Repertoire via Generative Adversarial Policy Networks


Title	Behavioural Repertoire via Generative Adversarial Policy Networks
Authors	Marija Jegorova, Stéphane Doncieux, Timothy Hospedales
Abstract	Learning algorithms are enabling robots to solve increasingly challenging real-world tasks. These approaches often rely on demonstrations and reproduce the behavior shown. Unexpected changes in the environment may require using different behaviors to achieve the same effect, for instance to reach and grasp an object in changing clutter. An emerging paradigm addressing this robustness issue is to learn a diverse set of successful behaviors for a given task, from which a robot can select the most suitable policy when faced with a new environment. In this paper, we explore a novel realization of this vision by learning a generative model over policies. Rather than learning a single policy, or a small fixed repertoire, our generative model for policies compactly encodes an unbounded number of policies and allows novel controller variants to be sampled. Leveraging our generative policy network, a robot can sample novel behaviors until it finds one that works for a new environment. We demonstrate this idea with an application of robust ball-throwing in the presence of obstacles. We show that this approach achieves a greater diversity of behaviors than an existing evolutionary approach, while maintaining good efficacy of sampled behaviors, allowing a Baxter robot to hit targets more often when ball throwing in the presence of obstacles.
Tasks
Published	2018-11-07
URL	https://arxiv.org/abs/1811.02945v3
PDF	https://arxiv.org/pdf/1811.02945v3.pdf
PWC	https://paperswithcode.com/paper/behavioural-repertoire-via-generative
Repo
Framework

Dimensionality Reduction of Hyperspectral Imagery Based on Spatial-spectral Manifold Learning


Title	Dimensionality Reduction of Hyperspectral Imagery Based on Spatial-spectral Manifold Learning
Authors	Hong Huang, Guangyao Shi, Haibo He, Yule Duan, Fulin Luo
Abstract	The graph embedding (GE) methods have been widely applied for dimensionality reduction of hyperspectral imagery (HSI). However, a major challenge of GE is how to choose proper neighbors for graph construction and explore the spatial information of HSI data. In this paper, we proposed an unsupervised dimensionality reduction algorithm termed spatial-spectral manifold reconstruction preserving embedding (SSMRPE) for HSI classification. At first, a weighted mean filter (WMF) is employed to preprocess the image, which aims to reduce the influence of background noise. According to the spatial consistency property of HSI, the SSMRPE method utilizes a new spatial-spectral combined distance (SSCD) to fuse the spatial structure and spectral information for selecting effective spatial-spectral neighbors of HSI pixels. Then, it explores the spatial relationship between each point and its neighbors to adjusts the reconstruction weights for improving the efficiency of manifold reconstruction. As a result, the proposed method can extract the discriminant features and subsequently improve the classification performance of HSI. The experimental results on PaviaU and Salinas hyperspectral datasets indicate that SSMRPE can achieve better classification accuracies in comparison with some state-of-the-art methods.
Tasks	Dimensionality Reduction, graph construction, Graph Embedding
Published	2018-12-22
URL	http://arxiv.org/abs/1812.09530v1
PDF	http://arxiv.org/pdf/1812.09530v1.pdf
PWC	https://paperswithcode.com/paper/dimensionality-reduction-of-hyperspectral
Repo
Framework

Resset: A Recurrent Model for Sequence of Sets with Applications to Electronic Medical Records


Title	Resset: A Recurrent Model for Sequence of Sets with Applications to Electronic Medical Records
Authors	Phuoc Nguyen, Truyen Tran, Svetha Venkatesh
Abstract	Modern healthcare is ripe for disruption by AI. A game changer would be automatic understanding the latent processes from electronic medical records, which are being collected for billions of people worldwide. However, these healthcare processes are complicated by the interaction between at least three dynamic components: the illness which involves multiple diseases, the care which involves multiple treatments, and the recording practice which is biased and erroneous. Existing methods are inadequate in capturing the dynamic structure of care. We propose Resset, an end-to-end recurrent model that reads medical record and predicts future risk. The model adopts the algebraic view in that discrete medical objects are embedded into continuous vectors lying in the same space. We formulate the problem as modeling sequences of sets, a novel setting that have rarely, if not, been addressed. Within Resset, the bag of diseases recorded at each clinic visit is modeled as function of sets. The same hold for the bag of treatments. The interaction between the disease bag and the treatment bag at a visit is modeled in several, one of which as residual of diseases minus the treatments. Finally, the health trajectory, which is a sequence of visits, is modeled using a recurrent neural network. We report results on over a hundred thousand hospital visits by patients suffered from two costly chronic diseases – diabetes and mental health. Resset shows promises in multiple predictive tasks such as readmission prediction, treatments recommendation and diseases progression.
Tasks	Readmission Prediction
Published	2018-02-03
URL	http://arxiv.org/abs/1802.00948v1
PDF	http://arxiv.org/pdf/1802.00948v1.pdf
PWC	https://paperswithcode.com/paper/resset-a-recurrent-model-for-sequence-of-sets
Repo
Framework

BshapeNet: Object Detection and Instance Segmentation with Bounding Shape Masks


Title	BshapeNet: Object Detection and Instance Segmentation with Bounding Shape Masks
Authors	Ba Rom Kang, Ha Young Kim
Abstract	Recent object detectors use four-coordinate bounding box (bbox) regression to predict object locations. Providing additional information indicating the object positions and coordinates will improve detection performance. Thus, we propose two types of masks: a bbox mask and a bounding shape (bshape) mask, to represent the object’s bbox and boundary shape, respectively. For each of these types, we consider two variants: the Thick model and the Scored model, both of which have the same morphology but differ in ways to make their boundaries thicker. To evaluate the proposed masks, we design extended frameworks by adding a bshape mask (or a bbox mask) branch to a Faster R-CNN framework, and call this BshapeNet (or BboxNet). Further, we propose BshapeNet+, a network that combines a bshape mask branch with a Mask R-CNN to improve instance segmentation as well as detection. Among our proposed models, BshapeNet+ demonstrates the best performance in both tasks and achieves highly competitive results with state of the art (SOTA) models. Particularly, it improves the detection results over Faster R-CNN+RoIAlign (37.3% and 28.9%) with a detection AP of 42.4% and 32.3% on MS COCO test-dev and Cityscapes val, respectively. Furthermore, for small objects, it achieves 24.9% AP on COCO test-dev, a significant improvement over previous SOTA models. For instance segmentation, it is substantially superior to Mask R-CNN on both test datasets.
Tasks	Instance Segmentation, Object Detection, Semantic Segmentation
Published	2018-10-15
URL	https://arxiv.org/abs/1810.10327v3
PDF	https://arxiv.org/pdf/1810.10327v3.pdf
PWC	https://paperswithcode.com/paper/bshapenet-object-detection-and-instance
Repo
Framework

Low-Cost Device Prototype for Automatic Medical Diagnosis Using Deep Learning Methods


Title	Low-Cost Device Prototype for Automatic Medical Diagnosis Using Deep Learning Methods
Authors	Neil Deshmukh
Abstract	This paper introduces a novel low-cost device prototype for the automatic diagnosis of diseases, utilizing inputted symptoms and personal background. The engineering goal is to solve the problem of limited healthcare access with a single device. Diagnosing diseases automatically is an immense challenge, owing to their variable properties and symptoms. On the other hand, Neural Networks have developed into a powerful tool in the field of machine learning, one that is showing to be extremely promising at computing diagnosis even with inconsistent variables. In this research, a cheap device was created to allow for straightforward diagnosis and treatment of human diseases. By utilizing Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs), outfitted on a Raspberry Pi Zero processor ($5), the device is able to detect up to 1537 different diseases and conditions and utilize a CNN for on-device visual diagnostics. The user can input the symptoms using the buttons on the device and can take pictures using the same mechanism. The algorithm processes inputted symptoms, providing diagnosis and possible treatment options for common conditions. The purpose of this work was to be able to diagnose diseases through an affordable processor with high accuracy, as it is currently achieving an accuracy of 90% for Top-5 symptom-based diagnoses, and 91% for visual skin diseases. The NNs achieve performance far above any other tested system, and its efficiency and ease of use will prove it to be a helpful tool for people around the world. This device could potentially provide low-cost universal access to vital diagnostics and treatment options.
Tasks	Medical Diagnosis
Published	2018-12-27
URL	http://arxiv.org/abs/1901.00751v2
PDF	http://arxiv.org/pdf/1901.00751v2.pdf
PWC	https://paperswithcode.com/paper/low-cost-device-prototype-for-automatic
Repo
Framework

Analysis of Speeches in Indian Parliamentary Debates


Title	Analysis of Speeches in Indian Parliamentary Debates
Authors	Sakala Venkata Krishna Rohit, Navjyoti Singh
Abstract	With the increasing usage of the internet, more and more data is being digitized including parliamentary debates but they are in an unstructured format. There is a need to convert them into a structured format for linguistic analysis. Much work has been done on parliamentary data such as Hansard, American congressional floor-debate data on various aspects but less on pragmatics. In this paper, we provide a dataset for the synopsis of Indian parliamentary debates and perform stance classification of speeches i.e identifying if the speaker is supporting the bill/issue or against it. We also analyze the intention of the speeches beyond mere sentences i.e pragmatics in the parliament. Based on thorough manual analysis of the debates, we developed an annotation scheme of 4 mutually exclusive categories to analyze the purpose of the speeches: to find out ISSUES, to BLAME, to APPRECIATE and for CALL FOR ACTION. We have annotated the dataset provided, with these 4 categories and conducted preliminary experiments for automatic detection of the categories. Our automated classification approach gave us promising results.
Tasks
Published	2018-08-21
URL	http://arxiv.org/abs/1808.06834v1
PDF	http://arxiv.org/pdf/1808.06834v1.pdf
PWC	https://paperswithcode.com/paper/analysis-of-speeches-in-indian-parliamentary
Repo
Framework

Deep LDA Hashing


Title	Deep LDA Hashing
Authors	Di Hu, Feiping Nie, Xuelong Li
Abstract	The conventional supervised hashing methods based on classification do not entirely meet the requirements of hashing technique, but Linear Discriminant Analysis (LDA) does. In this paper, we propose to perform a revised LDA objective over deep networks to learn efficient hashing codes in a truly end-to-end fashion. However, the complicated eigenvalue decomposition within each mini-batch in every epoch has to be faced with when simply optimizing the deep network w.r.t. the LDA objective. In this work, the revised LDA objective is transformed into a simple least square problem, which naturally overcomes the intractable problems and can be easily solved by the off-the-shelf optimizer. Such deep extension can also overcome the weakness of LDA Hashing in the limited linear projection and feature learning. Amounts of experiments are conducted on three benchmark datasets. The proposed Deep LDA Hashing shows nearly 70 points improvement over the conventional one on the CIFAR-10 dataset. It also beats several state-of-the-art methods on various metrics.
Tasks
Published	2018-10-08
URL	http://arxiv.org/abs/1810.03402v1
PDF	http://arxiv.org/pdf/1810.03402v1.pdf
PWC	https://paperswithcode.com/paper/deep-lda-hashing
Repo
Framework