Paper Group ANR 71
Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules. Understanding Negations in Information Processing: Learning from Replicating Human Behavior. Anomaly Detection in Hierarchical Data Streams under Unknown Models. Fundamental Conditions for Low-CP-Rank Tensor Completion. Named Entity Evolution Analysis on Wi …
Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules
| Title | Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules |
| Authors | Xinyang Feng, Jie Yang, Andrew F. Laine, Elsa D. Angelini |
| Abstract | Automated detection and segmentation of pulmonary nodules on lung computed tomography (CT) scans can facilitate early lung cancer diagnosis. Existing supervised approaches for automated nodule segmentation on CT scans require voxel-based annotations for training, which are labor- and time-consuming to obtain. In this work, we propose a weakly-supervised method that generates accurate voxel-level nodule segmentation trained with image-level labels only. By adapting a convolutional neural network (CNN) trained for image classification, our proposed method learns discriminative regions from the activation maps of convolution units at different scales, and identifies the true nodule location with a novel candidate-screening framework. Experimental results on the public LIDC-IDRI dataset demonstrate that, our weakly-supervised nodule segmentation framework achieves competitive performance compared to a fully-supervised CNN-based segmentation method. |
| Tasks | Computed Tomography (CT), Image Classification, Lung Cancer Diagnosis |
| Published | 2017-07-04 |
| URL | http://arxiv.org/abs/1707.01086v2 |
| http://arxiv.org/pdf/1707.01086v2.pdf | |
| PWC | https://paperswithcode.com/paper/discriminative-localization-in-cnns-for |
| Repo | |
| Framework | |
Understanding Negations in Information Processing: Learning from Replicating Human Behavior
| Title | Understanding Negations in Information Processing: Learning from Replicating Human Behavior |
| Authors | Nicolas Pröllochs, Stefan Feuerriegel, Dirk Neumann |
| Abstract | Information systems experience an ever-growing volume of unstructured data, particularly in the form of textual materials. This represents a rich source of information from which one can create value for people, organizations and businesses. For instance, recommender systems can benefit from automatically understanding preferences based on user reviews or social media. However, it is difficult for computer programs to correctly infer meaning from narrative content. One major challenge is negations that invert the interpretation of words and sentences. As a remedy, this paper proposes a novel learning strategy to detect negations: we apply reinforcement learning to find a policy that replicates the human perception of negations based on an exogenous response, such as a user rating for reviews. Our method yields several benefits, as it eliminates the former need for expensive and subjective manual labeling in an intermediate stage. Moreover, the inferred policy can be used to derive statistical inferences and implications regarding how humans process and act on negations. |
| Tasks | Recommendation Systems |
| Published | 2017-04-18 |
| URL | http://arxiv.org/abs/1704.05356v1 |
| http://arxiv.org/pdf/1704.05356v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-negations-in-information |
| Repo | |
| Framework | |
Anomaly Detection in Hierarchical Data Streams under Unknown Models
| Title | Anomaly Detection in Hierarchical Data Streams under Unknown Models |
| Authors | Sattar Vakili, Qing Zhao, Chang Liu, Chen-Nee Chuah |
| Abstract | We consider the problem of detecting a few targets among a large number of hierarchical data streams. The data streams are modeled as random processes with unknown and potentially heavy-tailed distributions. The objective is an active inference strategy that determines, sequentially, which data stream to collect samples from in order to minimize the sample complexity under a reliability constraint. We propose an active inference strategy that induces a biased random walk on the tree-structured hierarchy based on confidence bounds of sample statistics. We then establish its order optimality in terms of both the size of the search space (i.e., the number of data streams) and the reliability requirement. The results find applications in hierarchical heavy hitter detection, noisy group testing, and adaptive sampling for active learning, classification, and stochastic root finding. |
| Tasks | Active Learning, Anomaly Detection |
| Published | 2017-09-11 |
| URL | http://arxiv.org/abs/1709.03573v1 |
| http://arxiv.org/pdf/1709.03573v1.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-in-hierarchical-data |
| Repo | |
| Framework | |
Fundamental Conditions for Low-CP-Rank Tensor Completion
| Title | Fundamental Conditions for Low-CP-Rank Tensor Completion |
| Authors | Morteza Ashraphijuo, Xiaodong Wang |
| Abstract | We consider the problem of low canonical polyadic (CP) rank tensor completion. A completion is a tensor whose entries agree with the observed entries and its rank matches the given CP rank. We analyze the manifold structure corresponding to the tensors with the given rank and define a set of polynomials based on the sampling pattern and CP decomposition. Then, we show that finite completability of the sampled tensor is equivalent to having a certain number of algebraically independent polynomials among the defined polynomials. Our proposed approach results in characterizing the maximum number of algebraically independent polynomials in terms of a simple geometric structure of the sampling pattern, and therefore we obtain the deterministic necessary and sufficient condition on the sampling pattern for finite completability of the sampled tensor. Moreover, assuming that the entries of the tensor are sampled independently with probability $p$ and using the mentioned deterministic analysis, we propose a combinatorial method to derive a lower bound on the sampling probability $p$, or equivalently, the number of sampled entries that guarantees finite completability with high probability. We also show that the existing result for the matrix completion problem can be used to obtain a loose lower bound on the sampling probability $p$. In addition, we obtain deterministic and probabilistic conditions for unique completability. It is seen that the number of samples required for finite or unique completability obtained by the proposed analysis on the CP manifold is orders-of-magnitude lower than that is obtained by the existing analysis on the Grassmannian manifold. |
| Tasks | Matrix Completion |
| Published | 2017-03-31 |
| URL | http://arxiv.org/abs/1703.10740v1 |
| http://arxiv.org/pdf/1703.10740v1.pdf | |
| PWC | https://paperswithcode.com/paper/fundamental-conditions-for-low-cp-rank-tensor |
| Repo | |
| Framework | |
Named Entity Evolution Analysis on Wikipedia
| Title | Named Entity Evolution Analysis on Wikipedia |
| Authors | Helge Holzmann, Thomas Risse |
| Abstract | Accessing Web archives raises a number of issues caused by their temporal characteristics. Additional knowledge is needed to find and understand older texts. Especially entities mentioned in texts are subject to change. Most severe in terms of information retrieval are name changes. In order to find entities that have changed their name over time, search engines need to be aware of this evolution. We tackle this problem by analyzing Wikipedia in terms of entity evolutions mentioned in articles. We present statistical data on excerpts covering name changes, which will be used to discover similar text passages and extract evolution knowledge in future work. |
| Tasks | Information Retrieval |
| Published | 2017-02-03 |
| URL | http://arxiv.org/abs/1702.01176v1 |
| http://arxiv.org/pdf/1702.01176v1.pdf | |
| PWC | https://paperswithcode.com/paper/named-entity-evolution-analysis-on-wikipedia |
| Repo | |
| Framework | |
Explaining Transition Systems through Program Induction
| Title | Explaining Transition Systems through Program Induction |
| Authors | Svetlin Penkov, Subramanian Ramamoorthy |
| Abstract | Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and the formulation of more robust predictions. We propose to learn high level functional programs in order to represent abstract models which capture the invariant structure in the observed data. We introduce the $\pi$-machine (program-induction machine) – an architecture able to induce interpretable LISP-like programs from observed data traces. We propose an optimisation procedure for program learning based on backpropagation, gradient descent and A* search. We apply the proposed method to three problems: system identification of dynamical systems, explaining the behaviour of a DQN agent and learning by demonstration in a human-robot interaction scenario. Our experimental results show that the $\pi$-machine can efficiently induce interpretable programs from individual data traces. |
| Tasks | |
| Published | 2017-05-23 |
| URL | http://arxiv.org/abs/1705.08320v1 |
| http://arxiv.org/pdf/1705.08320v1.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-transition-systems-through-program |
| Repo | |
| Framework | |
Mining Electronic Health Records: A Survey
| Title | Mining Electronic Health Records: A Survey |
| Authors | Pranjul Yadav, Michael Steinbach, Vipin Kumar, Gyorgy Simon |
| Abstract | The continuously increasing cost of the US healthcare system has received significant attention. Central to the ideas aimed at curbing this trend is the use of technology, in the form of the mandate to implement electronic health records (EHRs). EHRs consist of patient information such as demographics, medications, laboratory test results, diagnosis codes and procedures. Mining EHRs could lead to improvement in patient health management as EHRs contain detailed information related to disease prognosis for large patient populations. In this manuscript, we provide a structured and comprehensive overview of data mining techniques for modeling EHR data. We first provide a detailed understanding of the major application areas to which EHR mining has been applied and then discuss the nature of EHR data and its accompanying challenges. Next, we describe major approaches used for EHR mining, the metrics associated with EHRs, and the various study designs. With this foundation, we then provide a systematic and methodological organization of existing data mining techniques used to model EHRs and discuss ideas for future research. We conclude this survey with a comprehensive summary of clinical data mining applications of EHR data, as illustrated in the online supplement. |
| Tasks | |
| Published | 2017-02-09 |
| URL | https://arxiv.org/abs/1702.03222v2 |
| https://arxiv.org/pdf/1702.03222v2.pdf | |
| PWC | https://paperswithcode.com/paper/mining-electronic-health-records-a-survey |
| Repo | |
| Framework | |
CAp 2017 challenge: Twitter Named Entity Recognition
| Title | CAp 2017 challenge: Twitter Named Entity Recognition |
| Authors | Cédric Lopez, Ioannis Partalas, Georgios Balikas, Nadia Derbas, Amélie Martin, Coralie Reutenauer, Frédérique Segond, Massih-Reza Amini |
| Abstract | The paper describes the CAp 2017 challenge. The challenge concerns the problem of Named Entity Recognition (NER) for tweets written in French. We first present the data preparation steps we followed for constructing the dataset released in the framework of the challenge. We begin by demonstrating why NER for tweets is a challenging problem especially when the number of entities increases. We detail the annotation process and the necessary decisions we made. We provide statistics on the inter-annotator agreement, and we conclude the data description part with examples and statistics for the data. We, then, describe the participation in the challenge, where 8 teams participated, with a focus on the methods employed by the challenge participants and the scores achieved in terms of F$_1$ measure. Importantly, the constructed dataset comprising $\sim$6,000 tweets annotated for 13 types of entities, which to the best of our knowledge is the first such dataset in French, is publicly available at \url{http://cap2017.imag.fr/competition.html} . |
| Tasks | Named Entity Recognition |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07568v1 |
| http://arxiv.org/pdf/1707.07568v1.pdf | |
| PWC | https://paperswithcode.com/paper/cap-2017-challenge-twitter-named-entity |
| Repo | |
| Framework | |
Efficient Noisy Optimisation with the Sliding Window Compact Genetic Algorithm
| Title | Efficient Noisy Optimisation with the Sliding Window Compact Genetic Algorithm |
| Authors | Simon M. Lucas, Jialin Liu, Diego Pérez-Liébana |
| Abstract | The compact genetic algorithm is an Estimation of Distribution Algorithm for binary optimisation problems. Unlike the standard Genetic Algorithm, no cross-over or mutation is involved. Instead, the compact Genetic Algorithm uses a virtual population represented as a probability distribution over the set of binary strings. At each optimisation iteration, exactly two individuals are generated by sampling from the distribution, and compared exactly once to determine a winner and a loser. The probability distribution is then adjusted to increase the likelihood of generating individuals similar to the winner. This paper introduces two straightforward variations of the compact Genetic Algorithm, each of which lead to a significant improvement in performance. The main idea is to make better use of each fitness evaluation, by ensuring that each evaluated individual is used in multiple win/loss comparisons. The first variation is to sample $n>2$ individuals at each iteration to make $n(n-1)/2$ comparisons. The second variation only samples one individual at each iteration but keeps a sliding history window of previous individuals to compare with. We evaluate methods on two noisy test problems and show that in each case they significantly outperform the compact Genetic Algorithm, while maintaining the simplicity of the algorithm. |
| Tasks | |
| Published | 2017-08-07 |
| URL | http://arxiv.org/abs/1708.02068v1 |
| http://arxiv.org/pdf/1708.02068v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-noisy-optimisation-with-the-sliding |
| Repo | |
| Framework | |
Towards Effective Low-bitwidth Convolutional Neural Networks
| Title | Towards Effective Low-bitwidth Convolutional Neural Networks |
| Authors | Bohan Zhuang, Chunhua Shen, Mingkui Tan, Lingqiao Liu, Ian Reid |
| Abstract | This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations. Optimizing a low-precision network is very challenging since the training process can easily get trapped in a poor local minima, which results in substantial accuracy loss. To mitigate this problem, we propose three simple-yet-effective approaches to improve the network training. First, we propose to use a two-stage optimization strategy to progressively find good local minima. Specifically, we propose to first optimize a net with quantized weights and then quantized activations. This is in contrast to the traditional methods which optimize them simultaneously. Second, following a similar spirit of the first method, we propose another progressive optimization approach which progressively decreases the bit-width from high-precision to low-precision during the course of training. Third, we adopt a novel learning scheme to jointly train a full-precision model alongside the low-precision one. By doing so, the full-precision model provides hints to guide the low-precision model training. Extensive experiments on various datasets ( i.e., CIFAR-100 and ImageNet) show the effectiveness of the proposed methods. To highlight, using our methods to train a 4-bit precision network leads to no performance decrease in comparison with its full-precision counterpart with standard network architectures ( i.e., AlexNet and ResNet-50). |
| Tasks | Quantization |
| Published | 2017-11-01 |
| URL | http://arxiv.org/abs/1711.00205v2 |
| http://arxiv.org/pdf/1711.00205v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-effective-low-bitwidth-convolutional |
| Repo | |
| Framework | |
Audiovisual Analytics Vocabulary and Ontology (AAVO): initial core and example expansion
| Title | Audiovisual Analytics Vocabulary and Ontology (AAVO): initial core and example expansion |
| Authors | Renato Fabbri, Maria Cristina Ferreira de Oliveira |
| Abstract | Visual Analytics might be defined as data mining assisted by interactive visual interfaces. The field has been receiving prominent consideration by researchers, developers and the industry. The literature, however, is complex because it involves multiple fields of knowledge and is considerably recent. In this article we describe an initial tentative organization of the knowledge in the field as an OWL ontology and a SKOS vocabulary. This effort might be useful in many ways that include conceptual considerations and software implementations. Within the results and discussions, we expose a core and an example expansion of the conceptualization, and incorporate design issues that enhance the expressive power of the abstraction. |
| Tasks | |
| Published | 2017-10-27 |
| URL | http://arxiv.org/abs/1710.09954v1 |
| http://arxiv.org/pdf/1710.09954v1.pdf | |
| PWC | https://paperswithcode.com/paper/audiovisual-analytics-vocabulary-and-ontology |
| Repo | |
| Framework | |
A Comprehensive Low and High-level Feature Analysis for Early Rumor Detection on Twitter
| Title | A Comprehensive Low and High-level Feature Analysis for Early Rumor Detection on Twitter |
| Authors | Tu Ngoc Nguyen |
| Abstract | Recent work have done a good job in modeling rumors and detecting them over microblog streams. However, the performance of their automatic approaches are not relatively high when looking early in the diffusion. A first intuition is that, at early stage, most of the aggregated rumor features (e.g., propagation features) are not mature and distinctive enough. The objective of rumor debunking in microblogs, however, are to detect these misinformation as early as possible. In this work, we leverage neural models in learning the hidden representations of individual rumor-related tweets at the very beginning of a rumor. Our extensive experiments show that the resulting signal improves our classification performance over time, significantly within the first 10 hours. To deepen the understanding of these low and high-level features in contributing to the model performance over time, we conduct an extensive study on a wide range of high impact rumor features for the 48 hours range. The end model that engages these features are shown to be competitive, reaches over 90% accuracy and out-performs strong baselines in our carefully cured dataset. |
| Tasks | |
| Published | 2017-11-02 |
| URL | http://arxiv.org/abs/1711.00726v2 |
| http://arxiv.org/pdf/1711.00726v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-comprehensive-low-and-high-level-feature |
| Repo | |
| Framework | |
Phonemic and Graphemic Multilingual CTC Based Speech Recognition
| Title | Phonemic and Graphemic Multilingual CTC Based Speech Recognition |
| Authors | Markus Müller, Sebastian Stüker, Alex Waibel |
| Abstract | Training automatic speech recognition (ASR) systems requires large amounts of data in the target language in order to achieve good performance. Whereas large training corpora are readily available for languages like English, there exists a long tail of languages which do suffer from a lack of resources. One method to handle data sparsity is to use data from additional source languages and build a multilingual system. Recently, ASR systems based on recurrent neural networks (RNNs) trained with connectionist temporal classification (CTC) have gained substantial research interest. In this work, we extended our previous approach towards training CTC-based systems multilingually. Our systems feature a global phone set, based on the joint phone sets of each source language. We evaluated the use of different language combinations as well as the addition of Language Feature Vectors (LFVs). As contrastive experiment, we built systems based on graphemes as well. Systems having a multilingual phone set are known to suffer in performance compared to their monolingual counterparts. With our proposed approach, we could reduce the gap between these mono- and multilingual setups, using either graphemes or phonemes. |
| Tasks | Speech Recognition |
| Published | 2017-11-13 |
| URL | http://arxiv.org/abs/1711.04564v1 |
| http://arxiv.org/pdf/1711.04564v1.pdf | |
| PWC | https://paperswithcode.com/paper/phonemic-and-graphemic-multilingual-ctc-based |
| Repo | |
| Framework | |
Her2 Challenge Contest: A Detailed Assessment of Automated Her2 Scoring Algorithms in Whole Slide Images of Breast Cancer Tissues
| Title | Her2 Challenge Contest: A Detailed Assessment of Automated Her2 Scoring Algorithms in Whole Slide Images of Breast Cancer Tissues |
| Authors | Talha Qaiser, Abhik Mukherjee, Chaitanya Reddy Pb, Sai Dileep Munugoti, Vamsi Tallam, Tomi Pitkäaho, Taina Lehtimäki, Thomas Naughton, Matt Berseth, Aníbal Pedraza, Ramakrishnan Mukundan, Matthew Smith, Abhir Bhalerao, Erik Rodner, Marcel Simon, Joachim Denzler, Chao-Hui Huang, Gloria Bueno, David Snead, Ian Ellis, Mohammad Ilyas, Nasir Rajpoot |
| Abstract | Evaluating expression of the Human epidermal growth factor receptor 2 (Her2) by visual examination of immunohistochemistry (IHC) on invasive breast cancer (BCa) is a key part of the diagnostic assessment of BCa due to its recognised importance as a predictive and prognostic marker in clinical practice. However, visual scoring of Her2 is subjective and consequently prone to inter-observer variability. Given the prognostic and therapeutic implications of Her2 scoring, a more objective method is required. In this paper, we report on a recent automated Her2 scoring contest, held in conjunction with the annual PathSoc meeting held in Nottingham in June 2016, aimed at systematically comparing and advancing the state-of-the-art Artificial Intelligence (AI) based automated methods for Her2 scoring. The contest dataset comprised of digitised whole slide images (WSI) of sections from 86 cases of invasive breast carcinoma stained with both Haematoxylin & Eosin (H&E) and IHC for Her2. The contesting algorithms automatically predicted scores of the IHC slides for an unseen subset of the dataset and the predicted scores were compared with the ‘ground truth’ (a consensus score from at least two experts). We also report on a simple Man vs Machine contest for the scoring of Her2 and show that the automated methods could beat the pathology experts on this contest dataset. This paper presents a benchmark for comparing the performance of automated algorithms for scoring of Her2. It also demonstrates the enormous potential of automated algorithms in assisting the pathologist with objective IHC scoring. |
| Tasks | |
| Published | 2017-05-23 |
| URL | http://arxiv.org/abs/1705.08369v3 |
| http://arxiv.org/pdf/1705.08369v3.pdf | |
| PWC | https://paperswithcode.com/paper/her2-challenge-contest-a-detailed-assessment |
| Repo | |
| Framework | |
Learning deep features for source color laser printer identification based on cascaded learning
| Title | Learning deep features for source color laser printer identification based on cascaded learning |
| Authors | Do-Guk Kim, Jong-Uk Hou, Heung-Kyu Lee |
| Abstract | Color laser printers have fast printing speed and high resolution, and forgeries using color laser printers can cause significant harm to society. A source printer identification technique can be employed as a countermeasure to those forgeries. This paper presents a color laser printer identification method based on cascaded learning of deep neural networks. The refiner network is trained by adversarial training to refine the synthetic dataset for halftone color decomposition. The halftone color decomposing ConvNet is trained with the refined dataset, and the trained knowledge is transferred to the printer identifying ConvNet to enhance the accuracy. The robustness about rotation and scaling is considered in training process, which is not considered in existing methods. Experiments are performed on eight color laser printers, and the performance is compared with several existing methods. The experimental results clearly show that the proposed method outperforms existing source color laser printer identification methods. |
| Tasks | |
| Published | 2017-11-01 |
| URL | http://arxiv.org/abs/1711.00207v1 |
| http://arxiv.org/pdf/1711.00207v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-deep-features-for-source-color-laser |
| Repo | |
| Framework | |
