Paper Group ANR 876
Polar $n$-Complex and $n$-Bicomplex Singular Value Decomposition and Principal Component Pursuit. Generating Self-Guided Dense Annotations for Weakly Supervised Semantic Segmentation. A Fast Deep Learning Model for Textual Relevance in Biomedical Information Retrieval. DeepCruiser: Automated Guided Testing for Stateful Deep Learning Systems. Micro- …
Polar $n$-Complex and $n$-Bicomplex Singular Value Decomposition and Principal Component Pursuit
Title | Polar $n$-Complex and $n$-Bicomplex Singular Value Decomposition and Principal Component Pursuit |
Authors | Tak-Shing T. Chan, Yi-Hsuan Yang |
Abstract | Informed by recent work on tensor singular value decomposition and circulant algebra matrices, this paper presents a new theoretical bridge that unifies the hypercomplex and tensor-based approaches to singular value decomposition and robust principal component analysis. We begin our work by extending the principal component pursuit to Olariu’s polar $n$-complex numbers as well as their bicomplex counterparts. In so doing, we have derived the polar $n$-complex and $n$-bicomplex proximity operators for both the $\ell_1$- and trace-norm regularizers, which can be used by proximal optimization methods such as the alternating direction method of multipliers. Experimental results on two sets of audio data show that our algebraically-informed formulation outperforms tensor robust principal component analysis. We conclude with the message that an informed definition of the trace norm can bridge the gap between the hypercomplex and tensor-based approaches. Our approach can be seen as a general methodology for generating other principal component pursuit algorithms with proper algebraic structures. |
Tasks | |
Published | 2018-01-09 |
URL | http://arxiv.org/abs/1801.03773v1 |
http://arxiv.org/pdf/1801.03773v1.pdf | |
PWC | https://paperswithcode.com/paper/polar-n-complex-and-n-bicomplex-singular |
Repo | |
Framework | |
Generating Self-Guided Dense Annotations for Weakly Supervised Semantic Segmentation
Title | Generating Self-Guided Dense Annotations for Weakly Supervised Semantic Segmentation |
Authors | Zi-Yi Ke, Chiou-Ting Hsu |
Abstract | Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to infer pseudo pixel-level labels for training semantic segmentation models. In this paper, we aim to develop a single neural network without resorting to any external models. We propose a novel self-guided strategy to fully utilize features learned across multiple levels to progressively generate the dense pseudo labels. First, we use high-level features as class-specific localization maps to roughly locate the classes. Next, we propose an affinity-guided method to encourage each localization map to be consistent with their intermediate level features. Third, we adopt the training image itself as guidance and propose a self-guided refinement to further transfer the image’s inherent structure into the maps. Finally, we derive pseudo pixel-level labels from these localization maps and use the pseudo labels as ground truth to train the semantic segmentation model. Our proposed self-guided strategy is a unified framework, which is built on a single network and alternatively updates the feature representation and refines localization maps during the training procedure. Experimental results on PASCAL VOC 2012 segmentation benchmark demonstrate that our method outperforms other weakly-supervised methods under the same setting. |
Tasks | Semantic Segmentation, Weakly-Supervised Semantic Segmentation |
Published | 2018-10-16 |
URL | http://arxiv.org/abs/1810.07050v1 |
http://arxiv.org/pdf/1810.07050v1.pdf | |
PWC | https://paperswithcode.com/paper/generating-self-guided-dense-annotations-for |
Repo | |
Framework | |
A Fast Deep Learning Model for Textual Relevance in Biomedical Information Retrieval
Title | A Fast Deep Learning Model for Textual Relevance in Biomedical Information Retrieval |
Authors | Sunil Mohan, Nicolas Fiorini, Sun Kim, Zhiyong Lu |
Abstract | Publications in the life sciences are characterized by a large technical vocabulary, with many lexical and semantic variations for expressing the same concept. Towards addressing the problem of relevance in biomedical literature search, we introduce a deep learning model for the relevance of a document’s text to a keyword style query. Limited by a relatively small amount of training data, the model uses pre-trained word embeddings. With these, the model first computes a variable-length Delta matrix between the query and document, representing a difference between the two texts, which is then passed through a deep convolution stage followed by a deep feed-forward network to compute a relevance score. This results in a fast model suitable for use in an online search engine. The model is robust and outperforms comparable state-of-the-art deep learning approaches. |
Tasks | Information Retrieval, Word Embeddings |
Published | 2018-02-26 |
URL | http://arxiv.org/abs/1802.10078v1 |
http://arxiv.org/pdf/1802.10078v1.pdf | |
PWC | https://paperswithcode.com/paper/a-fast-deep-learning-model-for-textual |
Repo | |
Framework | |
DeepCruiser: Automated Guided Testing for Stateful Deep Learning Systems
Title | DeepCruiser: Automated Guided Testing for Stateful Deep Learning Systems |
Authors | Xiaoning Du, Xiaofei Xie, Yi Li, Lei Ma, Jianjun Zhao, Yang Liu |
Abstract | Deep learning (DL) defines a data-driven programming paradigm that automatically composes the system decision logic from the training data. In company with the data explosion and hardware acceleration during the past decade, DL achieves tremendous success in many cutting-edge applications. However, even the state-of-the-art DL systems still suffer from quality and reliability issues. It was only until recently that some preliminary progress was made in testing feed-forward DL systems. In contrast to feed-forward DL systems, recurrent neural networks (RNN) follow a very different architectural design, implementing temporal behaviors and memory with loops and internal states. Such stateful nature of RNN contributes to its success in handling sequential inputs such as audio, natural languages and video processing, but also poses new challenges for quality assurance. In this paper, we initiate the very first step towards testing RNN-based stateful DL systems. We model RNN as an abstract state transition system, based on which we define a set of test coverage criteria specialized for stateful DL systems. Moreover, we propose an automated testing framework, DeepCruiser, which systematically generates tests in large scale to uncover defects of stateful DL systems with coverage guidance. Our in-depth evaluation on a state-of-the-art speech-to-text DL system demonstrates the effectiveness of our technique in improving quality and reliability of stateful DL systems. |
Tasks | |
Published | 2018-12-13 |
URL | http://arxiv.org/abs/1812.05339v1 |
http://arxiv.org/pdf/1812.05339v1.pdf | |
PWC | https://paperswithcode.com/paper/deepcruiser-automated-guided-testing-for |
Repo | |
Framework | |
Micro-Net: A unified model for segmentation of various objects in microscopy images
Title | Micro-Net: A unified model for segmentation of various objects in microscopy images |
Authors | Shan E Ahmed Raza, Linda Cheung, Muhammad Shaban, Simon Graham, David Epstein, Stella Pelengaris, Michael Khan, Nasir M. Rajpoot |
Abstract | Object segmentation and structure localization are important steps in automated image analysis pipelines for microscopy images. We present a convolution neural network (CNN) based deep learning architecture for segmentation of objects in microscopy images. The proposed network can be used to segment cells, nuclei and glands in fluorescence microscopy and histology images after slight tuning of input parameters. The network trains at multiple resolutions of the input image, connects the intermediate layers for better localization and context and generates the output using multi-resolution deconvolution filters. The extra convolutional layers which bypass the max-pooling operation allow the network to train for variable input intensities and object size and make it robust to noisy data. We compare our results on publicly available data sets and show that the proposed network outperforms recent deep learning algorithms. |
Tasks | Semantic Segmentation |
Published | 2018-04-22 |
URL | http://arxiv.org/abs/1804.08145v2 |
http://arxiv.org/pdf/1804.08145v2.pdf | |
PWC | https://paperswithcode.com/paper/micro-net-a-unified-model-for-segmentation-of |
Repo | |
Framework | |
Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models
Title | Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models |
Authors | Christoph Mayer, Radu Timofte, Grégory Paul |
Abstract | Generating training sets for deep convolutional neural networks (DCNNs) is a bottleneck for modern real-world applications. This is a demanding task for applications where annotating training data is costly, such as in semantic segmentation. In the literature, there is still a gap between the performance achieved by a network trained on full and on weak annotations. In this paper, we establish a strategy to measure this gap and to identify the ingredients necessary to reduce it. On scribbles, we establish new state-of-the-art results: we obtain a mIoU of 75.6% without, and 75.7% with CRF post-processing. We reduce the gap by 64.2% whereas the current state-of-the-art reduces it only by 57.5%. Thanks to a systematic study of the different ingredients involved in the weakly supervised scenario and an original experimental strategy, we unravel a counter-intuitive mechanism that is simple and amenable to generalisations to other weakly-supervised scenarios: averaging poor local predicted annotations with the baseline ones and reuse them for training a DCNN yields new state-of-the-art results. |
Tasks | Semantic Segmentation, Weakly-Supervised Semantic Segmentation |
Published | 2018-08-05 |
URL | http://arxiv.org/abs/1808.01625v3 |
http://arxiv.org/pdf/1808.01625v3.pdf | |
PWC | https://paperswithcode.com/paper/towards-closing-the-gap-in-weakly-supervised |
Repo | |
Framework | |
Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images
Title | Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images |
Authors | Tae Joon Jun, Dohyeun Kim, Daeyoung Kim |
Abstract | Pneumothorax is a relatively common disease, but in some cases, it may be difficult to find with chest radiography. In this paper, we propose a novel method of detecting pneumothorax in chest radiography. We propose an ensemble model of identical convolutional neural networks (CNN) with three different sizes of radiography images. Conventional methods may not properly characterize lost features while resizing large size images into 256 x 256 or 224 x 224 sizes. Our model is evaluated with ChestX-ray dataset which contains over 100,000 chest radiography images. As a result of the experiment, the proposed model showed AUC 0.911, which is the state of the art result in pneumothorax detection. Our method is expected to be effective when applying CNN to large size medical images. |
Tasks | |
Published | 2018-04-18 |
URL | http://arxiv.org/abs/1804.06821v1 |
http://arxiv.org/pdf/1804.06821v1.pdf | |
PWC | https://paperswithcode.com/paper/automated-diagnosis-of-pneumothorax-using-an |
Repo | |
Framework | |
Flow Network Tracking for Spatiotemporal and Periodic Point Matching: Applied to Cardiac Motion Analysis
Title | Flow Network Tracking for Spatiotemporal and Periodic Point Matching: Applied to Cardiac Motion Analysis |
Authors | Nripesh Parajuli, Allen Lu, Kevinminh Ta, John C. Stendahl, Nabil Boutagy, Imran Alkhalil, Melissa Eberle, Geng-Shi Jeng, Maria Zontak, Matthew ODonnell, Albert J. Sinusas, James S. Duncan |
Abstract | The accurate quantification of left ventricular (LV) deformation/strain shows significant promise for quantitatively assessing cardiac function for use in diagnosis and therapy planning (Jasaityte et al., 2013). However, accurate estimation of the displacement of myocardial tissue and hence LV strain has been challenging due to a variety of issues, including those related to deriving tracking tokens from images and following tissue locations over the entire cardiac cycle. In this work, we propose a point matching scheme where correspondences are modeled as flow through a graphical network. Myocardial surface points are set up as nodes in the network and edges define neighborhood relationships temporally. The novelty lies in the constraints that are imposed on the matching scheme, which render the correspondences one-to-one through the entire cardiac cycle, and not just two consecutive frames. The constraints also encourage motion to be cyclic, which is an important characteristic of LV motion. We validate our method by applying it to the estimation of quantitative LV displacement and strain estimation using 8 synthetic and 8 open-chested canine 4D echocardiographic image sequences, the latter with sonomicrometric crystals implanted on the LV wall. We were able to achieve excellent tracking accuracy on the synthetic dataset and observed a good correlation with crystal-based strains on the in-vivo data. |
Tasks | |
Published | 2018-07-09 |
URL | http://arxiv.org/abs/1807.02951v1 |
http://arxiv.org/pdf/1807.02951v1.pdf | |
PWC | https://paperswithcode.com/paper/flow-network-tracking-for-spatiotemporal-and |
Repo | |
Framework | |
Linguistic Search Optimization for Deep Learning Based LVCSR
Title | Linguistic Search Optimization for Deep Learning Based LVCSR |
Authors | Zhehuai Chen |
Abstract | Recent advances in deep learning based large vocabulary con- tinuous speech recognition (LVCSR) invoke growing demands in large scale speech transcription. The inference process of a speech recognizer is to find a sequence of labels whose corresponding acoustic and language models best match the input feature [1]. The main computation includes two stages: acoustic model (AM) inference and linguistic search (weighted finite-state transducer, WFST). Large computational overheads of both stages hamper the wide application of LVCSR. Benefit from stronger classifiers, deep learning, and more powerful computing devices, we propose general ideas and some initial trials to solve these fundamental problems. |
Tasks | Large Vocabulary Continuous Speech Recognition, Speech Recognition |
Published | 2018-08-02 |
URL | http://arxiv.org/abs/1808.00687v1 |
http://arxiv.org/pdf/1808.00687v1.pdf | |
PWC | https://paperswithcode.com/paper/linguistic-search-optimization-for-deep |
Repo | |
Framework | |
Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
Title | Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features |
Authors | Xiang Wang, Shaodi You, Xi Li, Huimin Ma |
Abstract | Weakly-supervised semantic segmentation under image tags supervision is a challenging task as it directly associates high-level semantic to low-level appearance. To bridge this gap, in this paper, we propose an iterative bottom-up and top-down framework which alternatively expands object regions and optimizes segmentation network. We start from initial localization produced by classification networks. While classification networks are only responsive to small and coarse discriminative object regions, we argue that, these regions contain significant common features about objects. So in the bottom-up step, we mine common object features from the initial localization and expand object regions with the mined features. To supplement non-discriminative regions, saliency maps are then considered under Bayesian framework to refine the object regions. Then in the top-down step, the refined object regions are used as supervision to train the segmentation network and to predict object masks. These object masks provide more accurate localization and contain more regions of object. Further, we take these object masks as initial localization and mine common object features from them. These processes are conducted iteratively to progressively produce fine object masks and optimize segmentation networks. Experimental results on Pascal VOC 2012 dataset demonstrate that the proposed method outperforms previous state-of-the-art methods by a large margin. |
Tasks | Semantic Segmentation, Weakly-Supervised Semantic Segmentation |
Published | 2018-06-12 |
URL | http://arxiv.org/abs/1806.04659v1 |
http://arxiv.org/pdf/1806.04659v1.pdf | |
PWC | https://paperswithcode.com/paper/weakly-supervised-semantic-segmentation-by |
Repo | |
Framework | |
Beyond Greedy Ranking: Slate Optimization via List-CVAE
Title | Beyond Greedy Ranking: Slate Optimization via List-CVAE |
Authors | Ray Jiang, Sven Gowal, Timothy A. Mann, Danilo J. Rezende |
Abstract | The conventional solution to the recommendation problem greedily ranks individual document candidates by prediction scores. However, this method fails to optimize the slate as a whole, and hence, often struggles to capture biases caused by the page layout and document interdepedencies. The slate recommendation problem aims to directly find the optimally ordered subset of documents (i.e. slates) that best serve users’ interests. Solving this problem is hard due to the combinatorial explosion in all combinations of document candidates and their display positions on the page. Therefore we propose a paradigm shift from the traditional viewpoint of solving a ranking problem to a direct slate generation framework. In this paper, we introduce List Conditional Variational Auto-Encoders (List-CVAE), which learns the joint distribution of documents on the slate conditioned on user responses, and directly generates full slates. Experiments on simulated and real-world data show that List-CVAE outperforms popular comparable ranking methods consistently on various scales of documents corpora. |
Tasks | |
Published | 2018-03-05 |
URL | http://arxiv.org/abs/1803.01682v6 |
http://arxiv.org/pdf/1803.01682v6.pdf | |
PWC | https://paperswithcode.com/paper/beyond-greedy-ranking-slate-optimization-via |
Repo | |
Framework | |
Demoiréing of Camera-Captured Screen Images Using Deep Convolutional Neural Network
Title | Demoiréing of Camera-Captured Screen Images Using Deep Convolutional Neural Network |
Authors | Bolin Liu, Xiao Shu, Xiaolin Wu |
Abstract | Taking photos of optoelectronic displays is a direct and spontaneous way of transferring data and keeping records, which is widely practiced. However, due to the analog signal interference between the pixel grids of the display screen and camera sensor array, objectionable moir'e (alias) patterns appear in captured screen images. As the moir'e patterns are structured and highly variant, they are difficult to be completely removed without affecting the underneath latent image. In this paper, we propose an approach of deep convolutional neural network for demoir'eing screen photos. The proposed DCNN consists of a coarse-scale network and a fine-scale network. In the coarse-scale network, the input image is first downsampled and then processed by stacked residual blocks to remove the moir'e artifacts. After that, the fine-scale network upsamples the demoir'ed low-resolution image back to the original resolution. Extensive experimental results have demonstrated that the proposed technique can efficiently remove the moir'e patterns for camera acquired screen images; the new technique outperforms the existing ones. |
Tasks | |
Published | 2018-04-11 |
URL | http://arxiv.org/abs/1804.03809v1 |
http://arxiv.org/pdf/1804.03809v1.pdf | |
PWC | https://paperswithcode.com/paper/demoireing-of-camera-captured-screen-images |
Repo | |
Framework | |
Neuromorphic Architecture for the Hierarchical Temporal Memory
Title | Neuromorphic Architecture for the Hierarchical Temporal Memory |
Authors | Abdullah M. Zyarah, Dhireesha Kudithipudi |
Abstract | A biomimetic machine intelligence algorithm, that holds promise in creating invariant representations of spatiotemporal input streams is the hierarchical temporal memory (HTM). This unsupervised online algorithm has been demonstrated on several machine-learning tasks, including anomaly detection. Significant effort has been made in formalizing and applying the HTM algorithm to different classes of problems. There are few early explorations of the HTM hardware architecture, especially for the earlier version of the spatial pooler of HTM algorithm. In this article, we present a full-scale HTM architecture for both spatial pooler and temporal memory. Synthetic synapse design is proposed to address the potential and dynamic interconnections occurring during learning. The architecture is interweaved with parallel cells and columns that enable high processing speed for the HTM. The proposed architecture is verified for two different datasets: MNIST and the European number plate font (EUNF), with and without the presence of noise. The spatial pooler architecture is synthesized on Xilinx ZYNQ-7, with 91.16% classification accuracy for MNIST and 90% accuracy for EUNF, with noise. For the temporal memory sequence prediction, first and second order predictions are observed for a 5-number long sequence generated from EUNF dataset and 95% accuracy is obtained. Moreover, the proposed hardware architecture offers 1364X speedup over the software realization. These results indicate that the proposed architecture can serve as a digital core to build the HTM in hardware and eventually as a standalone self-learning system. |
Tasks | Anomaly Detection |
Published | 2018-08-17 |
URL | http://arxiv.org/abs/1808.05839v1 |
http://arxiv.org/pdf/1808.05839v1.pdf | |
PWC | https://paperswithcode.com/paper/neuromorphic-architecture-for-the |
Repo | |
Framework | |
AGI Safety Literature Review
Title | AGI Safety Literature Review |
Authors | Tom Everitt, Gary Lea, Marcus Hutter |
Abstract | The development of Artificial General Intelligence (AGI) promises to be a major event. Along with its many potential benefits, it also raises serious safety concerns (Bostrom, 2014). The intention of this paper is to provide an easily accessible and up-to-date collection of references for the emerging field of AGI safety. A significant number of safety problems for AGI have been identified. We list these, and survey recent research on solving them. We also cover works on how best to think of AGI from the limited knowledge we have today, predictions for when AGI will first be created, and what will happen after its creation. Finally, we review the current public policy on AGI. |
Tasks | |
Published | 2018-05-03 |
URL | http://arxiv.org/abs/1805.01109v2 |
http://arxiv.org/pdf/1805.01109v2.pdf | |
PWC | https://paperswithcode.com/paper/agi-safety-literature-review |
Repo | |
Framework | |
Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data
Title | Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data |
Authors | Hugh Chen, Scott Lundberg, Su-In Lee |
Abstract | Time series data constitutes a distinct and growing problem in machine learning. As the corpus of time series data grows larger, deep models that simultaneously learn features and classify with these features can be intractable or suboptimal. In this paper, we present feature learning via long short term memory (LSTM) networks and prediction via gradient boosting trees (XGB). Focusing on the consequential setting of electronic health record data, we predict the occurrence of hypoxemia five minutes into the future based on past features. We make two observations: 1) long short term memory networks are effective at capturing long term dependencies based on a single feature and 2) gradient boosting trees are capable of tractably combining a large number of features including static features like height and weight. With these observations in mind, we generate features by performing “supervised” representation learning with LSTM networks. Augmenting the original XGB model with these features gives significantly better performance than either individual method. |
Tasks | Representation Learning, Time Series |
Published | 2018-01-23 |
URL | http://arxiv.org/abs/1801.07384v2 |
http://arxiv.org/pdf/1801.07384v2.pdf | |
PWC | https://paperswithcode.com/paper/hybrid-gradient-boosting-trees-and-neural |
Repo | |
Framework | |