Paper Group ANR 792
Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey. Deep Residual Text Detection Network for Scene Text. Multitask Learning with Deep Neural Networks for Community Question Answering. R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting. Automatic Classification of Cancerous Tissu …
Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey
| Title | Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey |
| Authors | Feiyun Zhu |
| Abstract | Hyperspectral unmixing (HU) is a very useful and increasingly popular preprocessing step for a wide range of hyperspectral applications. However, the HU research has been constrained a lot by three factors: (a) the number of hyperspectral images (especially the ones with ground truths) are very limited; (b) the ground truths of most hyperspectral images are not shared on the web, which may cause lots of unnecessary troubles for researchers to evaluate their algorithms; (c) the codes of most state-of-the-art methods are not shared, which may also delay the testing of new methods. Accordingly, this paper deals with the above issues from the following three perspectives: (1) as a profound contribution, we provide a general labeling method for the HU. With it, we labeled up to 15 hyperspectral images, providing 18 versions of ground truths. To the best of our knowledge, this is the first paper to summarize and share up to 15 hyperspectral images and their 18 versions of ground truths for the HU. Observing that the hyperspectral classification (HyC) has much more standard datasets (whose ground truths are generally publicly shared) than the HU, we propose an interesting method to transform the HyC datasets for the HU research. (2) To further facilitate the evaluation of HU methods under different conditions, we reviewed and implemented the algorithm to generate a complex synthetic hyperspectral image. By tuning the hyper-parameters in the code, we may verify the HU methods from four perspectives. The code would also be shared on the web. (3) To provide a standard comparison, we reviewed up to 10 state-of-the-art HU algorithms, then selected the 5 most benchmark HU algorithms, and compared them on the 15 real hyperspectral datasets. The experiment results are surely reproducible; the implemented codes would be shared on the web. |
| Tasks | Hyperspectral Unmixing |
| Published | 2017-08-17 |
| URL | http://arxiv.org/abs/1708.05125v2 |
| http://arxiv.org/pdf/1708.05125v2.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-unmixing-ground-truth-labeling |
| Repo | |
| Framework | |
Deep Residual Text Detection Network for Scene Text
| Title | Deep Residual Text Detection Network for Scene Text |
| Authors | Xiangyu Zhu, Yingying Jiang, Shuli Yang, Xiaobing Wang, Wei Li, Pei Fu, Hua Wang, Zhenbo Luo |
| Abstract | Scene text detection is a challenging problem in computer vision. In this paper, we propose a novel text detection network based on prevalent object detection frameworks. In order to obtain stronger semantic feature, we adopt ResNet as feature extraction layers and exploit multi-level feature by combining hierarchical convolutional networks. A vertical proposal mechanism is utilized to avoid proposal classification, while regression layer remains working to improve localization accuracy. Our approach evaluated on ICDAR2013 dataset achieves F-measure of 0.91, which outperforms previous state-of-the-art results in scene text detection. |
| Tasks | Object Detection, Scene Text Detection |
| Published | 2017-11-11 |
| URL | http://arxiv.org/abs/1711.04147v1 |
| http://arxiv.org/pdf/1711.04147v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-residual-text-detection-network-for |
| Repo | |
| Framework | |
Multitask Learning with Deep Neural Networks for Community Question Answering
| Title | Multitask Learning with Deep Neural Networks for Community Question Answering |
| Authors | Daniele Bonadiman, Antonio Uva, Alessandro Moschitti |
| Abstract | In this paper, we developed a deep neural network (DNN) that learns to solve simultaneously the three tasks of the cQA challenge proposed by the SemEval-2016 Task 3, i.e., question-comment similarity, question-question similarity and new question-comment similarity. The latter is the main task, which can exploit the previous two for achieving better results. Our DNN is trained jointly on all the three cQA tasks and learns to encode questions and comments into a single vector representation shared across the multiple tasks. The results on the official challenge test set show that our approach produces higher accuracy and faster convergence rates than the individual neural networks. Additionally, our method, which does not use any manual feature engineering, approaches the state of the art established with methods that make heavy use of it. |
| Tasks | Community Question Answering, Feature Engineering, Question Answering, Question Similarity |
| Published | 2017-02-13 |
| URL | http://arxiv.org/abs/1702.03706v1 |
| http://arxiv.org/pdf/1702.03706v1.pdf | |
| PWC | https://paperswithcode.com/paper/multitask-learning-with-deep-neural-networks |
| Repo | |
| Framework | |
R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting
| Title | R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting |
| Authors | Hardik Goel, Igor Melnyk, Arindam Banerjee |
| Abstract | Multivariate time-series modeling and forecasting is an important problem with numerous applications. Traditional approaches such as VAR (vector auto-regressive) models and more recent approaches such as RNNs (recurrent neural networks) are indispensable tools in modeling time-series data. In many multivariate time series modeling problems, there is usually a significant linear dependency component, for which VARs are suitable, and a nonlinear component, for which RNNs are suitable. Modeling such times series with only VAR or only RNNs can lead to poor predictive performance or complex models with large training times. In this work, we propose a hybrid model called R2N2 (Residual RNN), which first models the time series with a simple linear model (like VAR) and then models its residual errors using RNNs. R2N2s can be trained using existing algorithms for VARs and RNNs. Through an extensive empirical evaluation on two real world datasets (aviation and climate domains), we show that R2N2 is competitive, usually better than VAR or RNN, used alone. We also show that R2N2 is faster to train as compared to an RNN, while requiring less number of hidden units. |
| Tasks | Multivariate Time Series Forecasting, Time Series, Time Series Forecasting |
| Published | 2017-09-10 |
| URL | http://arxiv.org/abs/1709.03159v1 |
| http://arxiv.org/pdf/1709.03159v1.pdf | |
| PWC | https://paperswithcode.com/paper/r2n2-residual-recurrent-neural-networks-for |
| Repo | |
| Framework | |
Automatic Classification of Cancerous Tissue in Laserendomicroscopy Images of the Oral Cavity using Deep Learning
| Title | Automatic Classification of Cancerous Tissue in Laserendomicroscopy Images of the Oral Cavity using Deep Learning |
| Authors | Marc Aubreville, Christian Knipfer, Nicolai Oetter, Christian Jaremenko, Erik Rodner, Joachim Denzler, Christopher Bohr, Helmut Neumann, Florian Stelzle, Andreas Maier |
| Abstract | Oral Squamous Cell Carcinoma (OSCC) is a common type of cancer of the oral epithelium. Despite their high impact on mortality, sufficient screening methods for early diagnosis of OSCC often lack accuracy and thus OSCCs are mostly diagnosed at a late stage. Early detection and accurate outline estimation of OSCCs would lead to a better curative outcome and an reduction in recurrence rates after surgical treatment. Confocal Laser Endomicroscopy (CLE) records sub-surface micro-anatomical images for in vivo cell structure analysis. Recent CLE studies showed great prospects for a reliable, real-time ultrastructural imaging of OSCC in situ. We present and evaluate a novel automatic approach for a highly accurate OSCC diagnosis using deep learning technologies on CLE images. The method is compared against textural feature-based machine learning approaches that represent the current state of the art. For this work, CLE image sequences (7894 images) from patients diagnosed with OSCC were obtained from 4 specific locations in the oral cavity, including the OSCC lesion. The present approach is found to outperform the state of the art in CLE image recognition with an area under the curve (AUC) of 0.96 and a mean accuracy of 88.3% (sensitivity 86.6%, specificity 90%). |
| Tasks | |
| Published | 2017-03-05 |
| URL | http://arxiv.org/abs/1703.01622v2 |
| http://arxiv.org/pdf/1703.01622v2.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-classification-of-cancerous-tissue |
| Repo | |
| Framework | |
Deep learning for undersampled MRI reconstruction
| Title | Deep learning for undersampled MRI reconstruction |
| Authors | Chang Min Hyun, Hwa Pyung Kim, Sung Min Lee, Sungchul Lee, Jin Keun Seo |
| Abstract | This paper presents a deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and provides a rationale for why the proposed approach works well. Uniform subsampling is used in the time-consuming phase-encoding direction to capture high-resolution image information, while permitting the image-folding problem dictated by the Poisson summation formula. To deal with the localization uncertainty due to image folding, very few low-frequency k-space data are added. Training the deep learning net involves input and output images that are pairs of Fourier transforms of the subsampled and fully sampled k-space data. Numerous experiments show the remarkable performance of the proposed method; only 29% of k-space data can generate images of high quality as effectively as standard MRI reconstruction with fully sampled data. |
| Tasks | |
| Published | 2017-09-08 |
| URL | https://arxiv.org/abs/1709.02576v3 |
| https://arxiv.org/pdf/1709.02576v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-undersampled-mri |
| Repo | |
| Framework | |
Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning
| Title | Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning |
| Authors | Yacine Jernite, Samuel R. Bowman, David Sontag |
| Abstract | This work presents a novel objective function for the unsupervised training of neural network sentence encoders. It exploits signals from paragraph-level discourse coherence to train these models to understand text. Our objective is purely discriminative, allowing us to train models many times faster than was possible under prior methods, and it yields models which perform well in extrinsic evaluations. |
| Tasks | Representation Learning |
| Published | 2017-04-23 |
| URL | http://arxiv.org/abs/1705.00557v1 |
| http://arxiv.org/pdf/1705.00557v1.pdf | |
| PWC | https://paperswithcode.com/paper/discourse-based-objectives-for-fast |
| Repo | |
| Framework | |
Arc-Standard Spinal Parsing with Stack-LSTMs
| Title | Arc-Standard Spinal Parsing with Stack-LSTMs |
| Authors | Miguel Ballesteros, Xavier Carreras |
| Abstract | We present a neural transition-based parser for spinal trees, a dependency representation of constituent trees. The parser uses Stack-LSTMs that compose constituent nodes with dependency-based derivations. In experiments, we show that this model adapts to different styles of dependency relations, but this choice has little effect for predicting constituent structure, suggesting that LSTMs induce useful states by themselves. |
| Tasks | |
| Published | 2017-09-01 |
| URL | http://arxiv.org/abs/1709.00489v1 |
| http://arxiv.org/pdf/1709.00489v1.pdf | |
| PWC | https://paperswithcode.com/paper/arc-standard-spinal-parsing-with-stack-lstms |
| Repo | |
| Framework | |
A Human and Group Behaviour Simulation Evaluation Framework utilising Composition and Video Analysis
| Title | A Human and Group Behaviour Simulation Evaluation Framework utilising Composition and Video Analysis |
| Authors | Rob Dupre, Vasileios Argyriou |
| Abstract | In this work we present the modular Crowd Simulation Evaluation through Composition framework (CSEC) which provides a quantitative comparison between different pedestrian and crowd simulation approaches. Evaluation is made based on the comparison of source footage against synthetic video created through novel composition techniques. The proposed framework seeks to reduce the complexity of simulation evaluation and provide a platform from which the comparison of differing simulation algorithms as well as parametric tuning can be conducted to improve simulation accuracy or providing measures of similarity between crowd simulation algorithms and source data. Through the use of features designed to mimic the Human Visual System (HVS), specific simulation properties can be evaluated relative to sample footage. Validation was performed on a number of popular crowd datasets and through comparisons of multiple pedestrian and crowd simulation algorithms. |
| Tasks | |
| Published | 2017-07-09 |
| URL | http://arxiv.org/abs/1707.02655v3 |
| http://arxiv.org/pdf/1707.02655v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-human-and-group-behaviour-simulation |
| Repo | |
| Framework | |
Variational Inference using Implicit Distributions
| Title | Variational Inference using Implicit Distributions |
| Authors | Ferenc Huszár |
| Abstract | Generative adversarial networks (GANs) have given us a great tool to fit implicit generative models to data. Implicit distributions are ones we can sample from easily, and take derivatives of samples with respect to model parameters. These models are highly expressive and we argue they can prove just as useful for variational inference (VI) as they are for generative modelling. Several papers have proposed GAN-like algorithms for inference, however, connections to the theory of VI are not always well understood. This paper provides a unifying review of existing algorithms establishing connections between variational autoencoders, adversarially learned inference, operator VI, GAN-based image reconstruction, and more. Secondly, the paper provides a framework for building new algorithms: depending on the way the variational bound is expressed we introduce prior-contrastive and joint-contrastive methods, and show practical inference algorithms based on either density ratio estimation or denoising. |
| Tasks | Denoising, Image Reconstruction |
| Published | 2017-02-27 |
| URL | http://arxiv.org/abs/1702.08235v1 |
| http://arxiv.org/pdf/1702.08235v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-inference-using-implicit |
| Repo | |
| Framework | |
C3A: A Cognitive Collaborative Control Architecture For an Intelligent Wheelchair
| Title | C3A: A Cognitive Collaborative Control Architecture For an Intelligent Wheelchair |
| Authors | Rupam Bhattacharyya, Adity Saikia, Shyamanta M. Hazarika |
| Abstract | Retention of residual skills for persons who partially lose their cognitive or physical ability is of utmost importance. Research is focused on developing systems that provide need-based assistance for retention of such residual skills. This paper describes a novel cognitive collaborative control architecture C3A, designed to address the challenges of developing need- based assistance for wheelchair navigation. Organization of C3A is detailed and results from simulation of the proposed architecture is presented. For simulation of our proposed architecture, we have used ROS (Robot Operating System) as a control framework and a 3D robotic simulator called USARSim (Unified System for Automation and Robot Simulation). |
| Tasks | |
| Published | 2017-01-30 |
| URL | http://arxiv.org/abs/1701.08761v1 |
| http://arxiv.org/pdf/1701.08761v1.pdf | |
| PWC | https://paperswithcode.com/paper/c3a-a-cognitive-collaborative-control |
| Repo | |
| Framework | |
MaMaDroid: Detecting Android Malware by Building Markov Chains of Behavioral Models (Extended Version)
| Title | MaMaDroid: Detecting Android Malware by Building Markov Chains of Behavioral Models (Extended Version) |
| Authors | Lucky Onwuzurike, Enrico Mariconti, Panagiotis Andriotis, Emiliano De Cristofaro, Gordon Ross, Gianluca Stringhini |
| Abstract | As Android has become increasingly popular, so has malware targeting it, thus pushing the research community to propose different detection techniques. However, the constant evolution of the Android ecosystem, and of malware itself, makes it hard to design robust tools that can operate for long periods of time without the need for modifications or costly re-training. Aiming to address this issue, we set to detect malware from a behavioral point of view, modeled as the sequence of abstracted API calls. We introduce MaMaDroid, a static-analysis based system that abstracts the API calls performed by an app to their class, package, or family, and builds a model from their sequences obtained from the call graph of an app as Markov chains. This ensures that the model is more resilient to API changes and the features set is of manageable size. We evaluate MaMaDroid using a dataset of 8.5K benign and 35.5K malicious apps collected over a period of six years, showing that it effectively detects malware (with up to 0.99 F-measure) and keeps its detection capabilities for long periods of time (up to 0.87 F-measure two years after training). We also show that MaMaDroid remarkably outperforms DroidAPIMiner, a state-of-the-art detection system that relies on the frequency of (raw) API calls. Aiming to assess whether MaMaDroid’s effectiveness mainly stems from the API abstraction or from the sequencing modeling, we also evaluate a variant of it that uses frequency (instead of sequences), of abstracted API calls. We find that it is not as accurate, failing to capture maliciousness when trained on malware samples that include API calls that are equally or more frequently used by benign apps. |
| Tasks | |
| Published | 2017-11-20 |
| URL | http://arxiv.org/abs/1711.07477v2 |
| http://arxiv.org/pdf/1711.07477v2.pdf | |
| PWC | https://paperswithcode.com/paper/mamadroid-detecting-android-malware-by-1 |
| Repo | |
| Framework | |
Context aware saliency map generation using semantic segmentation
| Title | Context aware saliency map generation using semantic segmentation |
| Authors | Mahdi Ahmadi, Mohsen Hajabdollahi, Nader Karimi, Shadrokh Samavi |
| Abstract | Saliency map detection, as a method for detecting important regions of an image, is used in many applications such as image classification and recognition. We propose that context detection could have an essential role in image saliency detection. This requires extraction of high level features. In this paper a saliency map is proposed, based on image context detection using semantic segmentation as a high level feature. Saliency map from semantic information is fused with color and contrast based saliency maps. The final saliency map is then generated. Simulation results for Pascal-voc11 image dataset show 99% accuracy in context detection. Also final saliency map produced by our proposed method shows acceptable results in detecting salient points. |
| Tasks | Image Classification, Saliency Detection, Semantic Segmentation |
| Published | 2017-12-31 |
| URL | http://arxiv.org/abs/1801.00256v2 |
| http://arxiv.org/pdf/1801.00256v2.pdf | |
| PWC | https://paperswithcode.com/paper/context-aware-saliency-map-generation-using |
| Repo | |
| Framework | |
Synergistic Union of Word2Vec and Lexicon for Domain Specific Semantic Similarity
| Title | Synergistic Union of Word2Vec and Lexicon for Domain Specific Semantic Similarity |
| Authors | Keet Sugathadasa, Buddhi Ayesha, Nisansa de Silva, Amal Shehan Perera, Vindula Jayawardana, Dimuthu Lakmal, Madhavi Perera |
| Abstract | Semantic similarity measures are an important part in Natural Language Processing tasks. However Semantic similarity measures built for general use do not perform well within specific domains. Therefore in this study we introduce a domain specific semantic similarity measure that was created by the synergistic union of word2vec, a word embedding method that is used for semantic similarity calculation and lexicon based (lexical) semantic similarity methods. We prove that this proposed methodology out performs word embedding methods trained on generic corpus and methods trained on domain specific corpus but do not use lexical semantic similarity methods to augment the results. Further, we prove that text lemmatization can improve the performance of word embedding methods. |
| Tasks | Lemmatization, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-06-06 |
| URL | http://arxiv.org/abs/1706.01967v2 |
| http://arxiv.org/pdf/1706.01967v2.pdf | |
| PWC | https://paperswithcode.com/paper/synergistic-union-of-word2vec-and-lexicon-for |
| Repo | |
| Framework | |
Bayesian Decision Making in Groups is Hard
| Title | Bayesian Decision Making in Groups is Hard |
| Authors | Jan Hązła, Ali Jadbabaie, Elchanan Mossel, M. Amin Rahimian |
| Abstract | We study the computations that Bayesian agents undertake when exchanging opinions over a network. The agents act repeatedly on their private information and take myopic actions that maximize their expected utility according to a fully rational posterior belief. We show that such computations are NP-hard for two natural utility functions: one with binary actions, and another where agents reveal their posterior beliefs. In fact, we show that distinguishing between posteriors that are concentrated on different states of the world is NP-hard. Therefore, even approximating the Bayesian posterior beliefs is hard. We also describe a natural search algorithm to compute agents’ actions, which we call elimination of impossible signals, and show that if the network is transitive, the algorithm can be modified to run in polynomial time. |
| Tasks | Decision Making |
| Published | 2017-05-12 |
| URL | https://arxiv.org/abs/1705.04770v4 |
| https://arxiv.org/pdf/1705.04770v4.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-decision-making-in-groups-is-hard |
| Repo | |
| Framework | |
