January 31, 2020

3219 words 16 mins read

Paper Group ANR 172

Hierarchical stochastic neighbor embedding as a tool for visualizing the encoding capability of magnetic resonance fingerprinting dictionaries. Learning to Answer Ambiguous Questions with Knowledge Graph. Designing nanophotonic structures using conditional-deep convolutional generative adversarial networks. RinQ Fingerprinting: Recurrence-informed …

Hierarchical stochastic neighbor embedding as a tool for visualizing the encoding capability of magnetic resonance fingerprinting dictionaries


Title	Hierarchical stochastic neighbor embedding as a tool for visualizing the encoding capability of magnetic resonance fingerprinting dictionaries
Authors	Kirsten Koolstra, Peter Börnert, Boudewijn Lelieveldt, Andrew Webb, Oleh Dzyubachyk
Abstract	In Magnetic Resonance Fingerprinting (MRF) the quality of the estimated parameter maps depends on the encoding capability of the variable flip angle train. In this work we show how the dimensionality reduction technique Hierarchical Stochastic Neighbor Embedding (HSNE) can be used to obtain insight into the encoding capability of different MRF sequences. Embedding high-dimensional MRF dictionaries into a lower-dimensional space and visualizing them with colors, being a surrogate for location in low-dimensional space, provides a comprehensive overview of particular dictionaries and, in addition, enables comparison of different sequences. Dictionaries for various sequences and sequence lengths were compared to each other, and the effect of transmit field variations on the encoding capability was assessed. Clear differences in encoding capability were observed between different sequences, and HSNE results accurately reflect those obtained from an MRF matching simulation.
Tasks	Dimensionality Reduction, Magnetic Resonance Fingerprinting
Published	2019-10-07
URL	https://arxiv.org/abs/1910.02696v1
PDF	https://arxiv.org/pdf/1910.02696v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-stochastic-neighbor-embedding-as
Repo
Framework

Learning to Answer Ambiguous Questions with Knowledge Graph


Title	Learning to Answer Ambiguous Questions with Knowledge Graph
Authors	Yikai Zhu, Jianhao Shen, Ming Zhang
Abstract	In the task of factoid question answering over knowledge base, many questions have more than one plausible interpretation. Previous works on SimpleQuestions assume only one interpretation as the ground truth for each question, so they lack the ability to answer ambiguous questions correctly. In this paper, we present a new way to utilize the dataset that takes into account the existence of ambiguous questions. Then we introduce a simple and effective model which combines local knowledge subgraph with attention mechanism. Our experimental results show that our approach achieves outstanding performance in this task.
Tasks	Question Answering
Published	2019-12-25
URL	https://arxiv.org/abs/1912.11668v1
PDF	https://arxiv.org/pdf/1912.11668v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-answer-ambiguous-questions-with
Repo
Framework

Designing nanophotonic structures using conditional-deep convolutional generative adversarial networks


Title	Designing nanophotonic structures using conditional-deep convolutional generative adversarial networks
Authors	Sunae So, Junsuk Rho
Abstract	Data-driven design approaches based on deep-learning have been introduced in nanophotonics to reduce time-consuming iterative simulations which have been a major challenge. Here, we report the first use of conditional deep convolutional generative adversarial networks to design nanophotonic antennae that are not constrained to a predefined shape. For given input reflection spectra, the network generates desirable designs in the form of images; this form allows suggestions of new structures that cannot be represented by structural parameters. Simulation results obtained from the generated designs agreed well with the input reflection spectrum. This method opens new avenues towards the development of nanophotonics by providing a fast and convenient approach to design complex nanophotonic structures that have desired optical properties.
Tasks
Published	2019-03-20
URL	http://arxiv.org/abs/1903.08432v1
PDF	http://arxiv.org/pdf/1903.08432v1.pdf
PWC	https://paperswithcode.com/paper/designing-nanophotonic-structures-using
Repo
Framework

RinQ Fingerprinting: Recurrence-informed Quantile Networks for Magnetic Resonance Fingerprinting


Title	RinQ Fingerprinting: Recurrence-informed Quantile Networks for Magnetic Resonance Fingerprinting
Authors	Elisabeth Hoppe, Florian Thamm, Gregor Körzdörfer, Christopher Syben, Franziska Schirrmacher, Mathias Nittka, Josef Pfeuffer, Heiko Meyer, Andreas Maier
Abstract	Recently, Magnetic Resonance Fingerprinting (MRF) was proposed as a quantitative imaging technique for the simultaneous acquisition of tissue parameters such as relaxation times $T_1$ and $T_2$. Although the acquisition is highly accelerated, the state-of-the-art reconstruction suffers from long computation times: Template matching methods are used to find the most similar signal to the measured one by comparing it to pre-simulated signals of possible parameter combinations in a discretized dictionary. Deep learning approaches can overcome this limitation, by providing the direct mapping from the measured signal to the underlying parameters by one forward pass through a network. In this work, we propose a Recurrent Neural Network (RNN) architecture in combination with a novel quantile layer. RNNs are well suited for the processing of time-dependent signals and the quantile layer helps to overcome the noisy outliers by considering the spatial neighbors of the signal. We evaluate our approach using in-vivo data from multiple brain slices and several volunteers, running various experiments. We show that the RNN approach with small patches of complex-valued input signals in combination with a quantile layer outperforms other architectures, e.g. previously proposed CNNs for the MRF reconstruction reducing the error in $T_1$ and $T_2$ by more than 80%.
Tasks	Magnetic Resonance Fingerprinting
Published	2019-07-09
URL	https://arxiv.org/abs/1907.05277v2
PDF	https://arxiv.org/pdf/1907.05277v2.pdf
PWC	https://paperswithcode.com/paper/rinq-fingerprinting-recurrence-informed
Repo
Framework

Cover Detection using Dominant Melody Embeddings


Title	Cover Detection using Dominant Melody Embeddings
Authors	Guillaume Doras, Geoffroy Peeters
Abstract	Automatic cover detection – the task of finding in an audio database all the covers of one or several query tracks – has long been seen as a challenging theoretical problem in the MIR community and as an acute practical problem for authors and composers societies. Original algorithms proposed for this task have proven their accuracy on small datasets, but are unable to scale up to modern real-life audio corpora. On the other hand, faster approaches designed to process thousands of pairwise comparisons resulted in lower accuracy, making them unsuitable for practical use. In this work, we propose a neural network architecture that is trained to represent each track as a single embedding vector. The computation burden is therefore left to the embedding extraction – that can be conducted offline and stored, while the pairwise comparison task reduces to a simple Euclidean distance computation. We further propose to extract each track’s embedding out of its dominant melody representation, obtained by another neural network trained for this task. We then show that this architecture improves state-of-the-art accuracy both on small and large datasets, and is able to scale to query databases of thousands of tracks in a few seconds.
Tasks
Published	2019-07-03
URL	https://arxiv.org/abs/1907.01824v1
PDF	https://arxiv.org/pdf/1907.01824v1.pdf
PWC	https://paperswithcode.com/paper/cover-detection-using-dominant-melody
Repo
Framework

Advances in Natural Language Question Answering: A Review


Title	Advances in Natural Language Question Answering: A Review
Authors	K. S. D. Ishwari, A. K. R. R. Aneeze, S. Sudheesan, H. J. D. A. Karunaratne, A. Nugaliyadde, Y. Mallawarrachchi
Abstract	Question Answering has recently received high attention from artificial intelligence communities due to the advancements in learning technologies. Early question answering models used rule-based approaches and moved to the statistical approach to address the vastly available information. However, statistical approaches are shown to underperform in handling the dynamic nature and the variation of language. Therefore, learning models have shown the capability of handling the dynamic nature and variations in language. Many deep learning methods have been introduced to question answering. Most of the deep learning approaches have shown to achieve higher results compared to machine learning and statistical methods. The dynamic nature of language has profited from the nonlinear learning in deep learning. This has created prominent success and a spike in work on question answering. This paper discusses the successes and challenges in question answering question answering systems and techniques that are used in these challenges.
Tasks	Question Answering
Published	2019-04-10
URL	http://arxiv.org/abs/1904.05276v1
PDF	http://arxiv.org/pdf/1904.05276v1.pdf
PWC	https://paperswithcode.com/paper/advances-in-natural-language-question
Repo
Framework

Optimizing MRF-ASL Scan Design for Precise Quantification of Brain Hemodynamics using Neural Network Regression


Title	Optimizing MRF-ASL Scan Design for Precise Quantification of Brain Hemodynamics using Neural Network Regression
Authors	Anish Lahiri, Jeffrey A Fessler, Luis Hernandez-Garcia
Abstract	Purpose: Arterial Spin Labeling (ASL) is a quantitative, non-invasive alternative to perfusion imaging with contrast agents. Fixing values of certain model parameters in traditional ASL, which actually vary from region to region, may introduce bias in perfusion estimates. Adopting Magnetic Resonance Fingerprinting (MRF) for ASL is an alternative where these parameters are estimated alongside perfusion, but multiparametric estimation can degrade precision. We aim to improve the sensitivity of ASL-MRF signals to underlying parameters to counter this problem, and provide precise estimates. We also propose a regression based estimation framework for MRF-ASL. Methods: To improve the sensitivity of MRF-ASL signals to underlying parameters, we optimize ASL labeling durations using the Cramer-Rao Lower Bound (CRLB). This paper also proposes a neural network regression based estimation framework trained using noisy synthetic signals generated from our ASL signal model. Results: We test our methods in silico and in vivo, and compare with multiple post labeling delay (multi-PLD) ASL and unoptimized MRF-ASL. We present comparisons of estimated maps for six parameters accounted for in our signal model. Conclusions: The scan design process facilitates precise estimates of multiple hemodynamic parameters and tissue properties from a single scan, in regions of gray and white matter, as well as regions with anomalous perfusion activity in the brain. The regression based estimation approach provides perfusion estimates rapidly, and bypasses problems with quantization error. Keywords: Arterial Spin Labeling, Magnetic Resonance Fingerprinting, Optimization, Cramer-Rao Bound, Scan Design, Regression, Neural Networks, Deep Learning, Precision, Estimation, Brain Hemodynamics.
Tasks	Magnetic Resonance Fingerprinting, Quantization
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06474v1
PDF	https://arxiv.org/pdf/1905.06474v1.pdf
PWC	https://paperswithcode.com/paper/optimizing-mrf-asl-scan-design-for-precise
Repo
Framework

Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks


Title	Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks
Authors	Xiang He, Sibei Yang, Guanbin Li?, Haofeng Li, Huiyou Chang, Yizhou Yu
Abstract	Recent progress in biomedical image segmentation based on deep convolutional neural networks (CNNs) has drawn much attention. However, its vulnerability towards adversarial samples cannot be overlooked. This paper is the first one that discovers that all the CNN-based state-of-the-art biomedical image segmentation models are sensitive to adversarial perturbations. This limits the deployment of these methods in safety-critical biomedical fields. In this paper, we discover that global spatial dependencies and global contextual information in a biomedical image can be exploited to defend against adversarial attacks. To this end, non-local context encoder (NLCE) is proposed to model short- and long range spatial dependencies and encode global contexts for strengthening feature activations by channel-wise attention. The NLCE modules enhance the robustness and accuracy of the non-local context encoding network (NLCEN), which learns robust enhanced pyramid feature representations with NLCE modules, and then integrates the information across different levels. Experiments on both lung and skin lesion segmentation datasets have demonstrated that NLCEN outperforms any other state-of-the-art biomedical image segmentation methods against adversarial attacks. In addition, NLCE modules can be applied to improve the robustness of other CNN-based biomedical image segmentation methods.
Tasks	Lesion Segmentation, Semantic Segmentation
Published	2019-04-27
URL	http://arxiv.org/abs/1904.12181v1
PDF	http://arxiv.org/pdf/1904.12181v1.pdf
PWC	https://paperswithcode.com/paper/190412181
Repo
Framework

Differentiable Algorithm for Marginalising Changepoints


Title	Differentiable Algorithm for Marginalising Changepoints
Authors	Hyoungjin Lim, Gwonsoo Che, Wonyeol Lee, Hongseok Yang
Abstract	We present an algorithm for marginalising changepoints in time-series models that assume a fixed number of unknown changepoints. Our algorithm is differentiable with respect to its inputs, which are the values of latent random variables other than changepoints. Also, it runs in time O(mn) where n is the number of time steps and m the number of changepoints, an improvement over a naive marginalisation method with O(n^m) time complexity. We derive the algorithm by identifying quantities related to this marginalisation problem, showing that these quantities satisfy recursive relationships, and transforming the relationships to an algorithm via dynamic programming. Since our algorithm is differentiable, it can be applied to convert a model non-differentiable due to changepoints to a differentiable one, so that the resulting models can be analysed using gradient-based inference or learning techniques. We empirically show the effectiveness of our algorithm in this application by tackling the posterior inference problem on synthetic and real-world data.
Tasks	Time Series
Published	2019-11-22
URL	https://arxiv.org/abs/1911.09839v1
PDF	https://arxiv.org/pdf/1911.09839v1.pdf
PWC	https://paperswithcode.com/paper/differentiable-algorithm-for-marginalising
Repo
Framework

Population-based Global Optimisation Methods for Learning Long-term Dependencies with RNNs


Title	Population-based Global Optimisation Methods for Learning Long-term Dependencies with RNNs
Authors	Bryan Lim, Stefan Zohren, Stephen Roberts
Abstract	Despite recent innovations in network architectures and loss functions, training RNNs to learn long-term dependencies remains difficult due to challenges with gradient-based optimisation methods. Inspired by the success of Deep Neuroevolution in reinforcement learning (Such et al. 2017), we explore the use of gradient-free population-based global optimisation (PBO) techniques – training RNNs to capture long-term dependencies in time-series data. Testing evolution strategies (ES) and particle swarm optimisation (PSO) on an application in volatility forecasting, we demonstrate that PBO methods lead to performance improvements in general, with ES exhibiting the most consistent results across a variety of architectures.
Tasks	Time Series
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09691v1
PDF	https://arxiv.org/pdf/1905.09691v1.pdf
PWC	https://paperswithcode.com/paper/population-based-global-optimisation-methods
Repo
Framework

Interpretable and Generalizable Person Re-identification with Query-adaptive Convolution and Temporal Lifting


Title	Interpretable and Generalizable Person Re-identification with Query-adaptive Convolution and Temporal Lifting
Authors	Shengcai Liao, Ling Shao
Abstract	For person re-identification, existing deep networks often focus on representation learning. However, without domain adaptation or transfer learning, the learned model is fixed as is, which is not adaptable for handling various unseen scenarios. In this paper, beyond representation learning, we consider how to formulate person image matching directly in deep feature maps. We treat image matching as finding local correspondences in feature maps, and construct query-adaptive convolution kernels on the fly to achieve local matching. In this way, the matching process and result are interpretable, and this explicit matching is more generalizable than representation features to unseen scenarios, such as unknown misalignments, pose or viewpoint changes. To facilitate end-to-end training of this image matching architecture, we further build a class memory module to cache feature maps of the most recent samples of each class, so as to compute image matching losses for metric learning. Through direct cross-dataset evaluation without further transfer learning, the proposed Query-Adaptive Convolution (QAConv) method achieves better results than many transfer learning methods for person re-identification. Besides, a model-free temporal cooccurrence based score weighting method called TLift is proposed, which improves the performance to a further extent, resulting in state-of-the-art results in cross-dataset evaluations.
Tasks	Domain Adaptation, Face Recognition, Metric Learning, Person Re-Identification, Representation Learning, Transfer Learning
Published	2019-04-23
URL	https://arxiv.org/abs/1904.10424v2
PDF	https://arxiv.org/pdf/1904.10424v2.pdf
PWC	https://paperswithcode.com/paper/interpretable-and-generalizable-deep-image
Repo
Framework

Language Model Pre-training for Hierarchical Document Representations


Title	Language Model Pre-training for Hierarchical Document Representations
Authors	Ming-Wei Chang, Kristina Toutanova, Kenton Lee, Jacob Devlin
Abstract	Hierarchical neural architectures are often used to capture long-distance dependencies and have been applied to many document-level tasks such as summarization, document segmentation, and sentiment analysis. However, effective usage of such a large context can be difficult to learn, especially in the case where there is limited labeled data available. Building on the recent success of language model pretraining methods for learning flat representations of text, we propose algorithms for pre-training hierarchical document representations from unlabeled data. Unlike prior work, which has focused on pre-training contextual token representations or context-independent {sentence/paragraph} representations, our hierarchical document representations include fixed-length sentence/paragraph representations which integrate contextual information from the entire documents. Experiments on document segmentation, document-level question answering, and extractive document summarization demonstrate the effectiveness of the proposed pre-training algorithms.
Tasks	Document Summarization, Extractive Document Summarization, Language Modelling, Question Answering, Sentiment Analysis
Published	2019-01-26
URL	http://arxiv.org/abs/1901.09128v1
PDF	http://arxiv.org/pdf/1901.09128v1.pdf
PWC	https://paperswithcode.com/paper/language-model-pre-training-for-hierarchical
Repo
Framework

Learning with fuzzy hypergraphs: a topical approach to query-oriented text summarization


Title	Learning with fuzzy hypergraphs: a topical approach to query-oriented text summarization
Authors	Hadrien Van Lierde, Tommy W. S. Chow
Abstract	Existing graph-based methods for extractive document summarization represent sentences of a corpus as the nodes of a graph or a hypergraph in which edges depict relationships of lexical similarity between sentences. Such approaches fail to capture semantic similarities between sentences when they express a similar information but have few words in common and are thus lexically dissimilar. To overcome this issue, we propose to extract semantic similarities based on topical representations of sentences. Inspired by the Hierarchical Dirichlet Process, we propose a probabilistic topic model in order to infer topic distributions of sentences. As each topic defines a semantic connection among a group of sentences with a certain degree of membership for each sentence, we propose a fuzzy hypergraph model in which nodes are sentences and fuzzy hyperedges are topics. To produce an informative summary, we extract a set of sentences from the corpus by simultaneously maximizing their relevance to a user-defined query, their centrality in the fuzzy hypergraph and their coverage of topics present in the corpus. We formulate a polynomial time algorithm building on the theory of submodular functions to solve the associated optimization problem. A thorough comparative analysis with other graph-based summarization systems is included in the paper. Our obtained results show the superiority of our method in terms of content coverage of the summaries.
Tasks	Document Summarization, Extractive Document Summarization, Text Summarization
Published	2019-06-22
URL	https://arxiv.org/abs/1906.09445v1
PDF	https://arxiv.org/pdf/1906.09445v1.pdf
PWC	https://paperswithcode.com/paper/learning-with-fuzzy-hypergraphs-a-topical
Repo
Framework

On the Role of Geometry in Geo-Localization


Title	On the Role of Geometry in Geo-Localization
Authors	Moti Kadosh, Yael Moses, Ariel Shamir
Abstract	Humans can build a mental map of a geographical area to find their way and recognize places. The basic task we consider is geo-localization - finding the pose (position & orientation) of a camera in a large 3D scene from a single image. We aim to experimentally explore the role of geometry in geo-localization in a convolutional neural network (CNN) solution. We do so by ignoring the often available texture of the scene. We therefore deliberately avoid using texture or rich geometric details and use images projected from a simple 3D model of a city, which we term lean images. Lean images contain solely information that relates to the geometry of the area viewed (edges, faces, or relative depth). We find that the network is capable of estimating the camera pose from the lean images, and it does so not by memorization but by some measure of geometric learning of the geographical area. The main contributions of this paper are: (i) providing insight into the role of geometry in the CNN learning process; and (ii) demonstrating the power of CNNs for recovering camera pose using lean images.
Tasks
Published	2019-06-26
URL	https://arxiv.org/abs/1906.10855v1
PDF	https://arxiv.org/pdf/1906.10855v1.pdf
PWC	https://paperswithcode.com/paper/on-the-role-of-geometry-in-geo-localization
Repo
Framework

STC Speaker Recognition Systems for the VOiCES From a Distance Challenge


Title	STC Speaker Recognition Systems for the VOiCES From a Distance Challenge
Authors	Sergey Novoselov, Aleksei Gusev, Artem Ivanov, Timur Pekhovsky, Andrey Shulipa, Galina Lavrentyeva, Vladimir Volokhov, Alexandr Kozlov
Abstract	This paper presents the Speech Technology Center (STC) speaker recognition (SR) systems submitted to the VOiCES From a Distance challenge 2019. The challenge’s SR task is focused on the problem of speaker recognition in single channel distant/far-field audio under noisy conditions. In this work we investigate different deep neural networks architectures for speaker embedding extraction to solve the task. We show that deep networks with residual frame level connections outperform more shallow architectures. Simple energy based speech activity detector (SAD) and automatic speech recognition (ASR) based SAD are investigated in this work. We also address the problem of data preparation for robust embedding extractors training. The reverberation for the data augmentation was performed using automatic room impulse response generator. In our systems we used discriminatively trained cosine similarity metric learning model as embedding backend. Scores normalization procedure was applied for each individual subsystem we used. Our final submitted systems were based on the fusion of different subsystems. The results obtained on the VOiCES development and evaluation sets demonstrate effectiveness and robustness of the proposed systems when dealing with distant/far-field audio under noisy conditions.
Tasks	Data Augmentation, Metric Learning, Speaker Recognition, Speech Recognition
Published	2019-04-12
URL	http://arxiv.org/abs/1904.06093v1
PDF	http://arxiv.org/pdf/1904.06093v1.pdf
PWC	https://paperswithcode.com/paper/stc-speaker-recognition-systems-for-the
Repo
Framework