Paper Group ANR 667
Distributed Unmixing of Hyperspectral Data With Sparsity Constraint. Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space. pyLEMMINGS: Large Margin Multiple Instance Classification and Ranking for Bioinformatics Applications. 3D Object Classification via Spherical Projections. PROBE: Predi …
Distributed Unmixing of Hyperspectral Data With Sparsity Constraint
| Title | Distributed Unmixing of Hyperspectral Data With Sparsity Constraint |
| Authors | Sara Khoshsokhan, Roozbeh Rajabi, Hadi Zayyani |
| Abstract | Spectral unmixing (SU) is a data processing problem in hyperspectral remote sensing. The significant challenge in the SU problem is how to identify endmembers and their weights, accurately. For estimation of signature and fractional abundance matrices in a blind problem, nonnegative matrix factorization (NMF) and its developments are used widely in the SU problem. One of the constraints which was added to NMF is sparsity constraint that was regularized by L 1/2 norm. In this paper, a new algorithm based on distributed optimization has been used for spectral unmixing. In the proposed algorithm, a network including single-node clusters has been employed. Each pixel in hyperspectral images considered as a node in this network. The distributed unmixing with sparsity constraint has been optimized with diffusion LMS strategy, and then the update equations for fractional abundance and signature matrices are obtained. Simulation results based on defined performance metrics, illustrate advantage of the proposed algorithm in spectral unmixing of hyperspectral data compared with other methods. The results show that the AAD and SAD of the proposed approach are improved respectively about 6 and 27 percent toward distributed unmixing in SNR=25dB. |
| Tasks | Distributed Optimization |
| Published | 2017-11-03 |
| URL | http://arxiv.org/abs/1711.01249v1 |
| http://arxiv.org/pdf/1711.01249v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-unmixing-of-hyperspectral-data |
| Repo | |
| Framework | |
Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space
| Title | Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space |
| Authors | Liwei Wang, Alexander G. Schwing, Svetlana Lazebnik |
| Abstract | This paper explores image caption generation using conditional variational auto-encoders (CVAEs). Standard CVAEs with a fixed Gaussian prior yield descriptions with too little variability. Instead, we propose two models that explicitly structure the latent space around $K$ components corresponding to different types of image content, and combine components to create priors for images that contain multiple types of content simultaneously (e.g., several kinds of objects). Our first model uses a Gaussian Mixture model (GMM) prior, while the second one defines a novel Additive Gaussian (AG) prior that linearly combines component means. We show that both models produce captions that are more diverse and more accurate than a strong LSTM baseline or a “vanilla” CVAE with a fixed Gaussian prior, with AG-CVAE showing particular promise. |
| Tasks | |
| Published | 2017-11-19 |
| URL | http://arxiv.org/abs/1711.07068v1 |
| http://arxiv.org/pdf/1711.07068v1.pdf | |
| PWC | https://paperswithcode.com/paper/diverse-and-accurate-image-description-using |
| Repo | |
| Framework | |
pyLEMMINGS: Large Margin Multiple Instance Classification and Ranking for Bioinformatics Applications
| Title | pyLEMMINGS: Large Margin Multiple Instance Classification and Ranking for Bioinformatics Applications |
| Authors | Amina Asif, Wajid Arshad Abbasi, Farzeen Munir, Asa Ben-Hur, Fayyaz ul Amir Afsar Minhas |
| Abstract | Motivation: A major challenge in the development of machine learning based methods in computational biology is that data may not be accurately labeled due to the time and resources required for experimentally annotating properties of proteins and DNA sequences. Standard supervised learning algorithms assume accurate instance-level labeling of training data. Multiple instance learning is a paradigm for handling such labeling ambiguities. However, the widely used large-margin classification methods for multiple instance learning are heuristic in nature with high computational requirements. In this paper, we present stochastic sub-gradient optimization large margin algorithms for multiple instance classification and ranking, and provide them in a software suite called pyLEMMINGS. Results: We have tested pyLEMMINGS on a number of bioinformatics problems as well as benchmark datasets. pyLEMMINGS has successfully been able to identify functionally important segments of proteins: binding sites in Calmodulin binding proteins, prion forming regions, and amyloid cores. pyLEMMINGS achieves state-of-the-art performance in all these tasks, demonstrating the value of multiple instance learning. Furthermore, our method has shown more than 100-fold improvement in terms of running time as compared to heuristic solutions with improved accuracy over benchmark datasets. Availability and Implementation: pyLEMMINGS python package is available for download at: http://faculty.pieas.edu.pk/fayyaz/software.html#pylemmings. |
| Tasks | Multiple Instance Learning |
| Published | 2017-11-14 |
| URL | http://arxiv.org/abs/1711.04913v1 |
| http://arxiv.org/pdf/1711.04913v1.pdf | |
| PWC | https://paperswithcode.com/paper/pylemmings-large-margin-multiple-instance |
| Repo | |
| Framework | |
3D Object Classification via Spherical Projections
| Title | 3D Object Classification via Spherical Projections |
| Authors | Zhangjie Cao, Qixing Huang, Karthik Ramani |
| Abstract | In this paper, we introduce a new method for classifying 3D objects. Our main idea is to project a 3D object onto a spherical domain centered around its barycenter and develop neural network to classify the spherical projection. We introduce two complementary projections. The first captures depth variations of a 3D object, and the second captures contour-information viewed from different angles. Spherical projections combine key advantages of two main-stream 3D classification methods: image-based and 3D-based. Specifically, spherical projections are locally planar, allowing us to use massive image datasets (e.g, ImageNet) for pre-training. Also spherical projections are similar to voxel-based methods, as they encode complete information of a 3D object in a single neural network capturing dependencies across different views. Our novel network design can fully utilize these advantages. Experimental results on ModelNet40 and ShapeNetCore show that our method is superior to prior methods. |
| Tasks | 3D Object Classification, Object Classification |
| Published | 2017-12-12 |
| URL | http://arxiv.org/abs/1712.04426v1 |
| http://arxiv.org/pdf/1712.04426v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-object-classification-via-spherical |
| Repo | |
| Framework | |
PROBE: Predictive Robust Estimation for Visual-Inertial Navigation
| Title | PROBE: Predictive Robust Estimation for Visual-Inertial Navigation |
| Authors | Valentin Peretroukhin, Lee Clement, Matthew Giamou, Jonathan Kelly |
| Abstract | Navigation in unknown, chaotic environments continues to present a significant challenge for the robotics community. Lighting changes, self-similar textures, motion blur, and moving objects are all considerable stumbling blocks for state-of-the-art vision-based navigation algorithms. In this paper we present a novel technique for improving localization accuracy within a visual-inertial navigation system (VINS). We make use of training data to learn a model for the quality of visual features with respect to localization error in a given environment. This model maps each visual observation from a predefined prediction space of visual-inertial predictors onto a scalar weight, which is then used to scale the observation covariance matrix. In this way, our model can adjust the influence of each observation according to its quality. We discuss our choice of predictors and report substantial reductions in localization error on 4 km of data from the KITTI dataset, as well as on experimental datasets consisting of 700 m of indoor and outdoor driving on a small ground rover equipped with a Skybotix VI-Sensor. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://arxiv.org/abs/1708.00174v3 |
| https://arxiv.org/pdf/1708.00174v3.pdf | |
| PWC | https://paperswithcode.com/paper/probe-predictive-robust-estimation-for-visual |
| Repo | |
| Framework | |
Explaining Aviation Safety Incidents Using Deep Temporal Multiple Instance Learning
| Title | Explaining Aviation Safety Incidents Using Deep Temporal Multiple Instance Learning |
| Authors | Vijay Manikandan Janakiraman |
| Abstract | Although aviation accidents are rare, safety incidents occur more frequently and require a careful analysis to detect and mitigate risks in a timely manner. Analyzing safety incidents using operational data and producing event-based explanations is invaluable to airline companies as well as to governing organizations such as the Federal Aviation Administration (FAA) in the United States. However, this task is challenging because of the complexity involved in mining multi-dimensional heterogeneous time series data, the lack of time-step-wise annotation of events in a flight, and the lack of scalable tools to perform analysis over a large number of events. In this work, we propose a precursor mining algorithm that identifies events in the multidimensional time series that are correlated with the safety incident. Precursors are valuable to systems health and safety monitoring and in explaining and forecasting safety incidents. Current methods suffer from poor scalability to high dimensional time series data and are inefficient in capturing temporal behavior. We propose an approach by combining multiple-instance learning (MIL) and deep recurrent neural networks (DRNN) to take advantage of MIL’s ability to learn using weakly supervised data and DRNN’s ability to model temporal behavior. We describe the algorithm, the data, the intuition behind taking a MIL approach, and a comparative analysis of the proposed algorithm with baseline models. We also discuss the application to a real-world aviation safety problem using data from a commercial airline company and discuss the model’s abilities and shortcomings, with some final remarks about possible deployment directions. |
| Tasks | Multiple Instance Learning, Time Series |
| Published | 2017-10-12 |
| URL | http://arxiv.org/abs/1710.04749v2 |
| http://arxiv.org/pdf/1710.04749v2.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-aviation-safety-incidents-using |
| Repo | |
| Framework | |
A Streaming Accelerator for Deep Convolutional Neural Networks with Image and Feature Decomposition for Resource-limited System Applications
| Title | A Streaming Accelerator for Deep Convolutional Neural Networks with Image and Feature Decomposition for Resource-limited System Applications |
| Authors | Yuan Du, Li Du, Yilei Li, Junjie Su, Mau-Chung Frank Chang |
| Abstract | Deep convolutional neural networks (CNN) are widely used in modern artificial intelligence (AI) and smart vision systems but also limited by computation latency, throughput, and energy efficiency on a resource-limited scenario, such as mobile devices, internet of things (IoT), unmanned aerial vehicles (UAV), and so on. A hardware streaming architecture is proposed to accelerate convolution and pooling computations for state-of-the-art deep CNNs. It is optimized for energy efficiency by maximizing local data reuse to reduce off-chip DRAM data access. In addition, image and feature decomposition techniques are introduced to optimize memory access pattern for an arbitrary size of image and number of features within limited on-chip SRAM capacity. A prototype accelerator was implemented in TSMC 65 nm CMOS technology with 2.3 mm x 0.8 mm core area, which achieves 144 GOPS peak throughput and 0.8 TOPS/W peak energy efficiency. |
| Tasks | |
| Published | 2017-09-15 |
| URL | http://arxiv.org/abs/1709.05116v1 |
| http://arxiv.org/pdf/1709.05116v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-streaming-accelerator-for-deep |
| Repo | |
| Framework | |
MTDeep: Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defense
| Title | MTDeep: Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defense |
| Authors | Sailik Sengupta, Tathagata Chakraborti, Subbarao Kambhampati |
| Abstract | Present attack methods can make state-of-the-art classification systems based on deep neural networks misclassify every adversarially modified test example. The design of general defense strategies against a wide range of such attacks still remains a challenging problem. In this paper, we draw inspiration from the fields of cybersecurity and multi-agent systems and propose to leverage the concept of Moving Target Defense (MTD) in designing a meta-defense for ‘boosting’ the robustness of an ensemble of deep neural networks (DNNs) for visual classification tasks against such adversarial attacks. To classify an input image, a trained network is picked randomly from this set of networks by formulating the interaction between a Defender (who hosts the classification networks) and their (Legitimate and Malicious) users as a Bayesian Stackelberg Game (BSG). We empirically show that this approach, MTDeep, reduces misclassification on perturbed images in various datasets such as MNIST, FashionMNIST, and ImageNet while maintaining high classification accuracy on legitimate test images. We then demonstrate that our framework, being the first meta-defense technique, can be used in conjunction with any existing defense mechanism to provide more resilience against adversarial attacks that can be afforded by these defense mechanisms. Lastly, to quantify the increase in robustness of an ensemble-based classification system when we use MTDeep, we analyze the properties of a set of DNNs and introduce the concept of differential immunity that formalizes the notion of attack transferability. |
| Tasks | |
| Published | 2017-05-19 |
| URL | https://arxiv.org/abs/1705.07213v3 |
| https://arxiv.org/pdf/1705.07213v3.pdf | |
| PWC | https://paperswithcode.com/paper/mtdeep-boosting-the-security-of-deep-neural |
| Repo | |
| Framework | |
ProbFlow: Joint Optical Flow and Uncertainty Estimation
| Title | ProbFlow: Joint Optical Flow and Uncertainty Estimation |
| Authors | Anne S. Wannenwetsch, Margret Keuper, Stefan Roth |
| Abstract | Optical flow estimation remains challenging due to untextured areas, motion boundaries, occlusions, and more. Thus, the estimated flow is not equally reliable across the image. To that end, post-hoc confidence measures have been introduced to assess the per-pixel reliability of the flow. We overcome the artificial separation of optical flow and confidence estimation by introducing a method that jointly predicts optical flow and its underlying uncertainty. Starting from common energy-based formulations, we rely on the corresponding posterior distribution of the flow given the images. We derive a variational inference scheme based on mean field, which incorporates best practices from energy minimization. An uncertainty measure is obtained along the flow at every pixel as the (marginal) entropy of the variational distribution. We demonstrate the flexibility of our probabilistic approach by applying it to two different energies and on two benchmarks. We not only obtain flow results that are competitive with the underlying energy minimization approach, but also a reliable uncertainty measure that significantly outperforms existing post-hoc approaches. |
| Tasks | Optical Flow Estimation |
| Published | 2017-08-22 |
| URL | http://arxiv.org/abs/1708.06509v1 |
| http://arxiv.org/pdf/1708.06509v1.pdf | |
| PWC | https://paperswithcode.com/paper/probflow-joint-optical-flow-and-uncertainty |
| Repo | |
| Framework | |
SalNet360: Saliency Maps for omni-directional images with CNN
| Title | SalNet360: Saliency Maps for omni-directional images with CNN |
| Authors | Rafael Monroy, Sebastian Lutz, Tejo Chalasani, Aljosa Smolic |
| Abstract | The prediction of Visual Attention data from any kind of media is of valuable use to content creators and used to efficiently drive encoding algorithms. With the current trend in the Virtual Reality (VR) field, adapting known techniques to this new kind of media is starting to gain momentum. In this paper, we present an architectural extension to any Convolutional Neural Network (CNN) to fine-tune traditional 2D saliency prediction to Omnidirectional Images (ODIs) in an end-to-end manner. We show that each step in the proposed pipeline works towards making the generated saliency map more accurate with respect to ground truth data. |
| Tasks | Saliency Prediction |
| Published | 2017-09-19 |
| URL | http://arxiv.org/abs/1709.06505v2 |
| http://arxiv.org/pdf/1709.06505v2.pdf | |
| PWC | https://paperswithcode.com/paper/salnet360-saliency-maps-for-omni-directional |
| Repo | |
| Framework | |
Progressive Representation Adaptation for Weakly Supervised Object Localization
| Title | Progressive Representation Adaptation for Weakly Supervised Object Localization |
| Authors | Dong Li, Jia-Bin Huang, Yali Li, Shengjin Wang, Ming-Hsuan Yang |
| Abstract | We address the problem of weakly supervised object localization where only image-level annotations are available for training object detectors. Numerous methods have been proposed to tackle this problem through mining object proposals. However, a substantial amount of noise in object proposals causes ambiguities for learning discriminative object models. Such approaches are sensitive to model initialization and often converge to undesirable local minimum solutions. In this paper, we propose to overcome these drawbacks by progressive representation adaptation with two main steps: 1) classification adaptation and 2) detection adaptation. In classification adaptation, we transfer a pre-trained network to a multi-label classification task for recognizing the presence of a certain object in an image. Through the classification adaptation step, the network learns discriminative representations that are specific to object categories of interest. In detection adaptation, we mine class-specific object proposals by exploiting two scoring strategies based on the adapted classification network. Class-specific proposal mining helps remove substantial noise from the background clutter and potential confusion from similar objects. We further refine these proposals using multiple instance learning and segmentation cues. Using these refined object bounding boxes, we fine-tune all the layer of the classification network and obtain a fully adapted detection network. We present detailed experimental validation on the PASCAL VOC and ILSVRC datasets. Experimental results demonstrate that our progressive representation adaptation algorithm performs favorably against the state-of-the-art methods. |
| Tasks | Multi-Label Classification, Multiple Instance Learning, Object Localization, Weakly-Supervised Object Localization |
| Published | 2017-10-12 |
| URL | http://arxiv.org/abs/1710.04647v1 |
| http://arxiv.org/pdf/1710.04647v1.pdf | |
| PWC | https://paperswithcode.com/paper/progressive-representation-adaptation-for |
| Repo | |
| Framework | |
Stepwise Debugging of Answer-Set Programs
| Title | Stepwise Debugging of Answer-Set Programs |
| Authors | Johannes Oetsch, Jörg Pührer, Hans Tompits |
| Abstract | We introduce a stepping methodology for answer-set programming (ASP) that allows for debugging answer-set programs and is based on the stepwise application of rules. Similar to debugging in imperative languages, where the behaviour of a program is observed during a step-by-step execution, stepping for ASP allows for observing the effects that rule applications have in the computation of an answer set. While the approach is inspired from debugging in imperative programming, it is conceptually different to stepping in other paradigms due to non-determinism and declarativity that are inherent to ASP. In particular, unlike statements in an imperative program that are executed following a strict control flow, there is no predetermined order in which to consider rules in ASP during a computation. In our approach, the user is free to decide which rule to consider active in the next step following his or her intuition. This way, one can focus on interesting parts of the debugging search space. Bugs are detected during stepping by revealing differences between the actual semantics of the program and the expectations of the user. As a solid formal basis for stepping, we develop a framework of computations for answer-set programs. For fully supporting different solver languages, we build our framework on an abstract ASP language that is sufficiently general to capture different solver languages. To this end, we make use of abstract constraints as an established abstraction for popular language constructs such as aggregates. Stepping has been implemented in SeaLion, an integrated development environment for ASP. We illustrate stepping using an example scenario and discuss the stepping plugin of SeaLion. Moreover, we elaborate on methodological aspects and the embedding of stepping in the ASP development process. |
| Tasks | |
| Published | 2017-05-18 |
| URL | http://arxiv.org/abs/1705.06564v1 |
| http://arxiv.org/pdf/1705.06564v1.pdf | |
| PWC | https://paperswithcode.com/paper/stepwise-debugging-of-answer-set-programs |
| Repo | |
| Framework | |
Edina: Building an Open Domain Socialbot with Self-dialogues
| Title | Edina: Building an Open Domain Socialbot with Self-dialogues |
| Authors | Ben Krause, Marco Damonte, Mihai Dobre, Daniel Duma, Joachim Fainberg, Federico Fancellu, Emmanuel Kahembwe, Jianpeng Cheng, Bonnie Webber |
| Abstract | We present Edina, the University of Edinburgh’s social bot for the Amazon Alexa Prize competition. Edina is a conversational agent whose responses utilize data harvested from Amazon Mechanical Turk (AMT) through an innovative new technique we call self-dialogues. These are conversations in which a single AMT Worker plays both participants in a dialogue. Such dialogues are surprisingly natural, efficient to collect and reflective of relevant and/or trending topics. These self-dialogues provide training data for a generative neural network as well as a basis for soft rules used by a matching score component. Each match of a soft rule against a user utterance is associated with a confidence score which we show is strongly indicative of reply quality, allowing this component to self-censor and be effectively integrated with other components. Edina’s full architecture features a rule-based system backing off to a matching score, backing off to a generative neural network. Our hybrid data-driven methodology thus addresses both coverage limitations of a strictly rule-based approach and the lack of guarantees of a strictly machine-learning approach. |
| Tasks | |
| Published | 2017-09-28 |
| URL | http://arxiv.org/abs/1709.09816v1 |
| http://arxiv.org/pdf/1709.09816v1.pdf | |
| PWC | https://paperswithcode.com/paper/edina-building-an-open-domain-socialbot-with |
| Repo | |
| Framework | |
Model-based learning of local image features for unsupervised texture segmentation
| Title | Model-based learning of local image features for unsupervised texture segmentation |
| Authors | Martin Kiechle, Martin Storath, Andreas Weinmann, Martin Kleinsteuber |
| Abstract | Features that capture well the textural patterns of a certain class of images are crucial for the performance of texture segmentation methods. The manual selection of features or designing new ones can be a tedious task. Therefore, it is desirable to automatically adapt the features to a certain image or class of images. Typically, this requires a large set of training images with similar textures and ground truth segmentation. In this work, we propose a framework to learn features for texture segmentation when no such training data is available. The cost function for our learning process is constructed to match a commonly used segmentation model, the piecewise constant Mumford-Shah model. This means that the features are learned such that they provide an approximately piecewise constant feature image with a small jump set. Based on this idea, we develop a two-stage algorithm which first learns suitable convolutional features and then performs a segmentation. We note that the features can be learned from a small set of images, from a single image, or even from image patches. The proposed method achieves a competitive rank in the Prague texture segmentation benchmark, and it is effective for segmenting histological images. |
| Tasks | |
| Published | 2017-08-01 |
| URL | http://arxiv.org/abs/1708.00180v1 |
| http://arxiv.org/pdf/1708.00180v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-based-learning-of-local-image-features |
| Repo | |
| Framework | |
Database Learning: Toward a Database that Becomes Smarter Every Time
| Title | Database Learning: Toward a Database that Becomes Smarter Every Time |
| Authors | Yongjoo Park, Ahmad Shahab Tajik, Michael Cafarella, Barzan Mozafari |
| Abstract | In today’s databases, previous query answers rarely benefit answering future queries. For the first time, to the best of our knowledge, we change this paradigm in an approximate query processing (AQP) context. We make the following observation: the answer to each query reveals some degree of knowledge about the answer to another query because their answers stem from the same underlying distribution that has produced the entire dataset. Exploiting and refining this knowledge should allow us to answer queries more analytically, rather than by reading enormous amounts of raw data. Also, processing more queries should continuously enhance our knowledge of the underlying distribution, and hence lead to increasingly faster response times for future queries. We call this novel idea—learning from past query answers—Database Learning. We exploit the principle of maximum entropy to produce answers, which are in expectation guaranteed to be more accurate than existing sample-based approximations. Empowered by this idea, we build a query engine on top of Spark SQL, called Verdict. We conduct extensive experiments on real-world query traces from a large customer of a major database vendor. Our results demonstrate that Verdict supports 73.7% of these queries, speeding them up by up to 23.0x for the same accuracy level compared to existing AQP systems. |
| Tasks | |
| Published | 2017-03-16 |
| URL | http://arxiv.org/abs/1703.05468v2 |
| http://arxiv.org/pdf/1703.05468v2.pdf | |
| PWC | https://paperswithcode.com/paper/database-learning-toward-a-database-that |
| Repo | |
| Framework | |
