Paper Group ANR 1068
Stacked Neural Networks for end-to-end ciliary motion analysis. Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD. QoS aware Automatic Web Service Composition with Multiple objectives. Adversarial Regression with Multiple Learners. Auto-Detection of Safety Issues in Baby Products. Task Driven Generati …
Stacked Neural Networks for end-to-end ciliary motion analysis
Title | Stacked Neural Networks for end-to-end ciliary motion analysis |
Authors | Charles Lu, M. Marx, M. Zahid, C. W. Lo, C. Chennubhotla, S. P. Quinn |
Abstract | Cilia are hairlike structures protruding from nearly every cell in the body. Diseases known as ciliopathies, where cilia function is disrupted, can result in a wide spectrum of disorders. However, most techniques for assessing ciliary motion rely on manual identification and tracking of cilia; this process is laborious and error-prone, and does not scale well. Even where automated ciliary motion analysis tools exist, their applicability is limited. Here, we propose an end-to-end computational machine learning pipeline that automatically identifies regions of cilia from videos, extracts patches of cilia, and classifies patients as exhibiting normal or abnormal ciliary motion. In particular, we demonstrate how convolutional LSTM are able to encode complex features while remaining sensitive enough to differentiate between a variety of motion patterns. Our framework achieves 90% with only a few hundred training epochs. We find that the combination of segmentation and classification networks in a single pipeline yields performance comparable to existing computational pipelines, while providing the additional benefit of an end-to-end, fully-automated analysis toolbox for ciliary motion. |
Tasks | |
Published | 2018-03-20 |
URL | http://arxiv.org/abs/1803.07534v1 |
http://arxiv.org/pdf/1803.07534v1.pdf | |
PWC | https://paperswithcode.com/paper/stacked-neural-networks-for-end-to-end |
Repo | |
Framework | |
Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD
Title | Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD |
Authors | Jianyu Wang, Gauri Joshi |
Abstract | Large-scale machine learning training, in particular distributed stochastic gradient descent, needs to be robust to inherent system variability such as node straggling and random communication delays. This work considers a distributed training framework where each worker node is allowed to perform local model updates and the resulting models are averaged periodically. We analyze the true speed of error convergence with respect to wall-clock time (instead of the number of iterations), and analyze how it is affected by the frequency of averaging. The main contribution is the design of AdaComm, an adaptive communication strategy that starts with infrequent averaging to save communication delay and improve convergence speed, and then increases the communication frequency in order to achieve a low error floor. Rigorous experiments on training deep neural networks show that AdaComm can take $3 \times$ less time than fully synchronous SGD, and still reach the same final training loss. |
Tasks | |
Published | 2018-10-19 |
URL | http://arxiv.org/abs/1810.08313v2 |
http://arxiv.org/pdf/1810.08313v2.pdf | |
PWC | https://paperswithcode.com/paper/adaptive-communication-strategies-to-achieve |
Repo | |
Framework | |
QoS aware Automatic Web Service Composition with Multiple objectives
Title | QoS aware Automatic Web Service Composition with Multiple objectives |
Authors | Soumi Chattopadhyay, Ansuman Banerjee |
Abstract | With an increasing number of web services, providing an end-to-end Quality of Service (QoS) guarantee in responding to user queries is becoming an important concern. Multiple QoS parameters (e.g., response time, latency, throughput, reliability, availability, success rate) are associated with a service, thereby, service composition with a large number of candidate services is a challenging multi-objective optimization problem. In this paper, we study the multi-constrained multi-objective QoS aware web service composition problem and propose three different approaches to solve the same, one optimal, based on Pareto front construction and two other based on heuristically traversing the solution space. We compare the performance of the heuristics against the optimal, and show the effectiveness of our proposals over other classical approaches for the same problem setting, with experiments on WSC-2009 and ICEBE-2005 datasets. |
Tasks | |
Published | 2018-09-07 |
URL | http://arxiv.org/abs/1809.02317v1 |
http://arxiv.org/pdf/1809.02317v1.pdf | |
PWC | https://paperswithcode.com/paper/qos-aware-automatic-web-service-composition |
Repo | |
Framework | |
Adversarial Regression with Multiple Learners
Title | Adversarial Regression with Multiple Learners |
Authors | Liang Tong, Sixie Yu, Scott Alfeld, Yevgeniy Vorobeychik |
Abstract | Despite the considerable success enjoyed by machine learning techniques in practice, numerous studies demonstrated that many approaches are vulnerable to attacks. An important class of such attacks involves adversaries changing features at test time to cause incorrect predictions. Previous investigations of this problem pit a single learner against an adversary. However, in many situations an adversary’s decision is aimed at a collection of learners, rather than specifically targeted at each independently. We study the problem of adversarial linear regression with multiple learners. We approximate the resulting game by exhibiting an upper bound on learner loss functions, and show that the resulting game has a unique symmetric equilibrium. We present an algorithm for computing this equilibrium, and show through extensive experiments that equilibrium models are significantly more robust than conventional regularized linear regression. |
Tasks | |
Published | 2018-06-06 |
URL | http://arxiv.org/abs/1806.02256v1 |
http://arxiv.org/pdf/1806.02256v1.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-regression-with-multiple-learners |
Repo | |
Framework | |
Auto-Detection of Safety Issues in Baby Products
Title | Auto-Detection of Safety Issues in Baby Products |
Authors | Graham Bleaney, Matthew Kuzyk, Julian Man, Hossein Mayanloo, H. R. Tizhoosh |
Abstract | Every year, thousands of people receive consumer product related injuries. Research indicates that online customer reviews can be processed to autonomously identify product safety issues. Early identification of safety issues can lead to earlier recalls, and thus fewer injuries and deaths. A dataset of product reviews from Amazon.com was compiled, along with \emph{SaferProducts.gov} complaints and recall descriptions from the Consumer Product Safety Commission (CPSC) and European Commission Rapid Alert system. A system was built to clean the collected text and to extract relevant features. Dimensionality reduction was performed by computing feature relevance through a Random Forest and discarding features with low information gain. Various classifiers were analyzed, including Logistic Regression, SVMs, Na{"i}ve-Bayes, Random Forests, and an Ensemble classifier. Experimentation with various features and classifier combinations resulted in a logistic regression model with 66% precision in the top 50 reviews surfaced. This classifier outperforms all benchmarks set by related literature and consumer product safety professionals. |
Tasks | Dimensionality Reduction |
Published | 2018-04-27 |
URL | http://arxiv.org/abs/1805.09772v2 |
http://arxiv.org/pdf/1805.09772v2.pdf | |
PWC | https://paperswithcode.com/paper/auto-detection-of-safety-issues-in-baby |
Repo | |
Framework | |
Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
Title | Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation |
Authors | Yue Zhang, Shun Miao, Tommaso Mansi, Rui Liao |
Abstract | Automatic parsing of anatomical objects in X-ray images is critical to many clinical applications in particular towards image-guided invention and workflow automation. Existing deep network models require a large amount of labeled data. However, obtaining accurate pixel-wise labeling in X-ray images relies heavily on skilled clinicians due to the large overlaps of anatomy and the complex texture patterns. On the other hand, organs in 3D CT scans preserve clearer structures as well as sharper boundaries and thus can be easily delineated. In this paper, we propose a novel model framework for learning automatic X-ray image parsing from labeled CT scans. Specifically, a Dense Image-to-Image network (DI2I) for multi-organ segmentation is first trained on X-ray like Digitally Reconstructed Radiographs (DRRs) rendered from 3D CT volumes. Then we introduce a Task Driven Generative Adversarial Network (TD-GAN) architecture to achieve simultaneous style transfer and parsing for unseen real X-ray images. TD-GAN consists of a modified cycle-GAN substructure for pixel-to-pixel translation between DRRs and X-ray images and an added module leveraging the pre-trained DI2I to enforce segmentation consistency. The TD-GAN framework is general and can be easily adapted to other learning tasks. In the numerical experiments, we validate the proposed model on 815 DRRs and 153 topograms. While the vanilla DI2I without any adaptation fails completely on segmenting the topograms, the proposed model does not require any topogram labels and is able to provide a promising average dice of 85% which achieves the same level accuracy of supervised training (88%). |
Tasks | Domain Adaptation, Semantic Segmentation, Style Transfer, Unsupervised Domain Adaptation |
Published | 2018-06-11 |
URL | http://arxiv.org/abs/1806.07201v1 |
http://arxiv.org/pdf/1806.07201v1.pdf | |
PWC | https://paperswithcode.com/paper/task-driven-generative-modeling-for |
Repo | |
Framework | |
Scene Learning: Deep Convolutional Networks For Wind Power Prediction by Embedding Turbines into Grid Space
Title | Scene Learning: Deep Convolutional Networks For Wind Power Prediction by Embedding Turbines into Grid Space |
Authors | Ruiguo Yu, Zhiqiang Liu, Xuewei Li, Wenhuan Lu, Mei Yu, Jianrong Wang, Bin Li |
Abstract | Wind power prediction is of vital importance in wind power utilization. There have been a lot of researches based on the time series of the wind power or speed, but In fact, these time series cannot express the temporal and spatial changes of wind, which fundamentally hinders the advance of wind power prediction. In this paper, a new kind of feature that can describe the process of temporal and spatial variation is proposed, namely, Spatio-Temporal Features. We first map the data collected at each moment from the wind turbine to the plane to form the state map, namely, the scene, according to the relative positions. The scene time series over a period of time is a multi-channel image, i.e. the Spatio-Temporal Features. Based on the Spatio-Temporal Features, the deep convolutional network is applied to predict the wind power, achieving a far better accuracy than the existing methods. Compared with the starge-of-the-art method, the mean-square error (MSE) in our method is reduced by 49.83%, and the average time cost for training models can be shortened by a factor of more than 150. |
Tasks | Time Series |
Published | 2018-07-16 |
URL | http://arxiv.org/abs/1807.05666v2 |
http://arxiv.org/pdf/1807.05666v2.pdf | |
PWC | https://paperswithcode.com/paper/scene-learning-deep-convolutional-networks |
Repo | |
Framework | |
A Reliability Theory of Truth
Title | A Reliability Theory of Truth |
Authors | Karl Schlechta |
Abstract | Our approach is basically a coherence approach, but we avoid the well-known pitfalls of coherence theories of truth. Consistency is replaced by reliability, which expresses support and attack, and, in principle, every theory (or agent, message) counts. At the same time, we do not require a priviledged access to “reality”. A centerpiece of our approach is that we attribute reliability also to agents, messages, etc., so an unreliable source of information will be less important in future. Our ideas can also be extended to value systems, and even actions, e.g., of animals. |
Tasks | |
Published | 2018-01-03 |
URL | http://arxiv.org/abs/1801.01788v3 |
http://arxiv.org/pdf/1801.01788v3.pdf | |
PWC | https://paperswithcode.com/paper/a-reliability-theory-of-truth |
Repo | |
Framework | |
Nonlinear Dynamics of Binocular Rivalry: A Comparative Study
Title | Nonlinear Dynamics of Binocular Rivalry: A Comparative Study |
Authors | Yashaswini Murthy |
Abstract | When our eyes are presented with the same image, the brain processes it to view it as a single coherent one. The lateral shift in the position of our eyes, causes the two images to possess certain differences, which our brain exploits for the purpose of depth perception and to gauge the size of objects at different distances, a process commonly known as stereopsis. However, when presented with two different visual stimuli, the visual awareness alternates. This phenomenon of binocular rivalry is a result of competition between the corresponding neuronal populations of the two eyes. The article presents a comparative study of various dynamical models proposed to capture this process. It goes on to study the effect of a certain parameter on the rate of perceptual alternations and proceeds to disprove the initial propositions laid down to characterise this phenomenon. It concludes with a discussion on the possible future work that can be conducted to obtain a better picture of the neuronal functioning behind this rivalry. |
Tasks | |
Published | 2018-11-25 |
URL | http://arxiv.org/abs/1811.10005v1 |
http://arxiv.org/pdf/1811.10005v1.pdf | |
PWC | https://paperswithcode.com/paper/nonlinear-dynamics-of-binocular-rivalry-a |
Repo | |
Framework | |
PersEmoN: A Deep Network for Joint Analysis of Apparent Personality, Emotion and Their Relationship
Title | PersEmoN: A Deep Network for Joint Analysis of Apparent Personality, Emotion and Their Relationship |
Authors | Le Zhang, Songyou Peng, Stefan Winkler |
Abstract | Apparent personality and emotion analysis are both central to affective computing. Existing works solve them individually. In this paper we investigate if such high-level affect traits and their relationship can be jointly learned from face images in the wild. To this end, we introduce PersEmoN, an end-to-end trainable and deep Siamese-like network. It consists of two convolutional network branches, one for emotion and the other for apparent personality. Both networks share their bottom feature extraction module and are optimized within a multi-task learning framework. Emotion and personality networks are dedicated to their own annotated dataset. Furthermore, an adversarial-like loss function is employed to promote representation coherence among heterogeneous dataset sources. Based on this, we also explore the emotion-to-apparent-personality relationship. Extensive experiments demonstrate the effectiveness of PersEmoN. |
Tasks | Emotion Recognition, Multi-Task Learning |
Published | 2018-11-21 |
URL | https://arxiv.org/abs/1811.08657v2 |
https://arxiv.org/pdf/1811.08657v2.pdf | |
PWC | https://paperswithcode.com/paper/persemon-a-deep-network-for-joint-analysis-of |
Repo | |
Framework | |
Implicit Reparameterization Gradients
Title | Implicit Reparameterization Gradients |
Authors | Michael Figurnov, Shakir Mohamed, Andriy Mnih |
Abstract | By providing a simple and efficient way of computing low-variance gradients of continuous random variables, the reparameterization trick has become the technique of choice for training a variety of latent variable models. However, it is not applicable to a number of important continuous distributions. We introduce an alternative approach to computing reparameterization gradients based on implicit differentiation and demonstrate its broader applicability by applying it to Gamma, Beta, Dirichlet, and von Mises distributions, which cannot be used with the classic reparameterization trick. Our experiments show that the proposed approach is faster and more accurate than the existing gradient estimators for these distributions. |
Tasks | Latent Variable Models |
Published | 2018-05-22 |
URL | http://arxiv.org/abs/1805.08498v4 |
http://arxiv.org/pdf/1805.08498v4.pdf | |
PWC | https://paperswithcode.com/paper/implicit-reparameterization-gradients |
Repo | |
Framework | |
Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
Title | Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization |
Authors | Bruno Korbar, Du Tran, Lorenzo Torresani |
Abstract | There is a natural correlation between the visual and auditive elements of a video. In this work we leverage this connection to learn general and effective models for both audio and video analysis from self-supervised temporal synchronization. We demonstrate that a calibrated curriculum learning scheme, a careful choice of negative examples, and the use of a contrastive loss are critical ingredients to obtain powerful multi-sensory representations from models optimized to discern temporal synchronization of audio-video pairs. Without further finetuning, the resulting audio features achieve performance superior or comparable to the state-of-the-art on established audio classification benchmarks (DCASE2014 and ESC-50). At the same time, our visual subnet provides a very effective initialization to improve the accuracy of video-based action recognition models: compared to learning from scratch, our self-supervised pretraining yields a remarkable gain of +19.9% in action recognition accuracy on UCF101 and a boost of +17.7% on HMDB51. |
Tasks | Audio Classification, Temporal Action Localization |
Published | 2018-06-30 |
URL | http://arxiv.org/abs/1807.00230v2 |
http://arxiv.org/pdf/1807.00230v2.pdf | |
PWC | https://paperswithcode.com/paper/cooperative-learning-of-audio-and-video |
Repo | |
Framework | |
An Efficient Image Retrieval Based on Fusion of Low-Level Visual Features
Title | An Efficient Image Retrieval Based on Fusion of Low-Level Visual Features |
Authors | Atif Nazir, Kashif Nazir |
Abstract | Due to an increase in the number of image achieves, Content-Based Image Retrieval (CBIR) has gained attention for research community of computer vision. The image visual contents are represented in a feature space in the form of numerical values that is considered as a feature vector of image. Images belonging to different classes may contain the common visuals and shapes that can result in the closeness of computed feature space of two different images belonging to separate classes. Due to this reason, feature extraction and image representation is selected with appropriate features as it directly affects the performance of image retrieval system. The commonly used visual features are image spatial layout, color, texture and shape. Image feature space is combined to achieve the discriminating ability that is not possible to achieve when the features are used separately. Due to this reason, in this paper, we aim to explore the low-level feature combination that are based on color and shape features. We selected color moments and color histogram to represent color while shape is represented by using invariant moments. We selected this combination, as these features are reported intuitive, compact and robust for image representation. We evaluated the performance of our proposed research by using the Corel, Coil and Ground Truth (GT) image datasets. We evaluated the proposed low-level feature fusion by calculating the precision, recall and time required for feature extraction. The precision, recall and feature extraction values obtained from the proposed low-level feature fusion outperforms the existing research of CBIR. |
Tasks | Content-Based Image Retrieval, Image Retrieval |
Published | 2018-11-30 |
URL | http://arxiv.org/abs/1811.12695v1 |
http://arxiv.org/pdf/1811.12695v1.pdf | |
PWC | https://paperswithcode.com/paper/an-efficient-image-retrieval-based-on-fusion |
Repo | |
Framework | |
What’s to know? Uncertainty as a Guide to Asking Goal-oriented Questions
Title | What’s to know? Uncertainty as a Guide to Asking Goal-oriented Questions |
Authors | Ehsan Abbasnejad, Qi Wu, Javen Shi, Anton van den Hengel |
Abstract | One of the core challenges in Visual Dialogue problems is asking the question that will provide the most useful information towards achieving the required objective. Encouraging an agent to ask the right questions is difficult because we don’t know a-priori what information the agent will need to achieve its task, and we don’t have an explicit model of what it knows already. We propose a solution to this problem based on a Bayesian model of the uncertainty in the implicit model maintained by the visual dialogue agent, and in the function used to select an appropriate output. By selecting the question that minimises the predicted regret with respect to this implicit model the agent actively reduces ambiguity. The Bayesian model of uncertainty also enables a principled method for identifying when enough information has been acquired, and an action should be selected. We evaluate our approach on two goal-oriented dialogue datasets, one for visual-based collaboration task and the other for a negotiation-based task. Our uncertainty-aware information-seeking model outperforms its counterparts in these two challenging problems. |
Tasks | Visual Dialog |
Published | 2018-12-16 |
URL | http://arxiv.org/abs/1812.06401v1 |
http://arxiv.org/pdf/1812.06401v1.pdf | |
PWC | https://paperswithcode.com/paper/whats-to-know-uncertainty-as-a-guide-to |
Repo | |
Framework | |
Knockoff Nets: Stealing Functionality of Black-Box Models
Title | Knockoff Nets: Stealing Functionality of Black-Box Models |
Authors | Tribhuvanesh Orekondy, Bernt Schiele, Mario Fritz |
Abstract | Machine Learning (ML) models are increasingly deployed in the wild to perform a wide range of tasks. In this work, we ask to what extent can an adversary steal functionality of such “victim” models based solely on blackbox interactions: image in, predictions out. In contrast to prior work, we present an adversary lacking knowledge of train/test data used by the model, its internals, and semantics over model outputs. We formulate model functionality stealing as a two-step approach: (i) querying a set of input images to the blackbox model to obtain predictions; and (ii) training a “knockoff” with queried image-prediction pairs. We make multiple remarkable observations: (a) querying random images from a different distribution than that of the blackbox training data results in a well-performing knockoff; (b) this is possible even when the knockoff is represented using a different architecture; and (c) our reinforcement learning approach additionally improves query sample efficiency in certain settings and provides performance gains. We validate model functionality stealing on a range of datasets and tasks, as well as on a popular image analysis API where we create a reasonable knockoff for as little as $30. |
Tasks | |
Published | 2018-12-06 |
URL | http://arxiv.org/abs/1812.02766v1 |
http://arxiv.org/pdf/1812.02766v1.pdf | |
PWC | https://paperswithcode.com/paper/knockoff-nets-stealing-functionality-of-black |
Repo | |
Framework | |