Paper Group AWR 8
Fast, Precise Myelin Water Quantification using DESS MRI and Kernel Learning. Iterative Document Representation Learning Towards Summarization with Polishing. Unsupervised domain adaptation for medical imaging segmentation with self-ensembling. Sparsity-based Defense against Adversarial Attacks on Linear Classifiers. Gated Fusion Network for Joint …
Fast, Precise Myelin Water Quantification using DESS MRI and Kernel Learning
Title | Fast, Precise Myelin Water Quantification using DESS MRI and Kernel Learning |
Authors | Gopal Nataraj, Jon-Fredrik Nielsen, Mingjie Gao, Jeffrey A. Fessler |
Abstract | Purpose: To investigate the feasibility of myelin water content quantification using fast dual-echo steady-state (DESS) scans and machine learning with kernels. Methods: We optimized combinations of steady-state (SS) scans for precisely estimating the fast-relaxing signal fraction ff of a two-compartment signal model, subject to a scan time constraint. We estimated ff from the optimized DESS acquisition using a recently developed method for rapid parameter estimation via regression with kernels (PERK). We compared DESS PERK ff estimates to conventional myelin water fraction (MWF) estimates from a longer multi-echo spin-echo (MESE) acquisition in simulation, in vivo, and ex vivo studies. Results: Simulations demonstrate that DESS PERK ff estimators and MESE MWF estimators achieve comparable error levels. In vivo and ex vivo experiments demonstrate that MESE MWF and DESS PERK ff estimates are quantitatively comparable measures of WM myelin water content. To our knowledge, these experiments are the first to demonstrate myelin water images from a SS acquisition that are quantitatively similar to conventional MESE MWF images. Conclusion: Combinations of fast DESS scans can be designed to enable precise ff estimation. PERK is well-suited for ff estimation. DESS PERK ff and MESE MWF estimates are quantitatively similar measures of WM myelin water content. |
Tasks | |
Published | 2018-09-24 |
URL | http://arxiv.org/abs/1809.08908v1 |
http://arxiv.org/pdf/1809.08908v1.pdf | |
PWC | https://paperswithcode.com/paper/fast-precise-myelin-water-quantification |
Repo | https://github.com/gopal-nataraj/mwf |
Framework | none |
Iterative Document Representation Learning Towards Summarization with Polishing
Title | Iterative Document Representation Learning Towards Summarization with Polishing |
Authors | Xiuying Chen, Shen Gao, Chongyang Tao, Yan Song, Dongyan Zhao, Rui Yan |
Abstract | In this paper, we introduce Iterative Text Summarization (ITS), an iteration-based model for supervised extractive text summarization, inspired by the observation that it is often necessary for a human to read an article multiple times in order to fully understand and summarize its contents. Current summarization approaches read through a document only once to generate a document representation, resulting in a sub-optimal representation. To address this issue we introduce a model which iteratively polishes the document representation on many passes through the document. As part of our model, we also introduce a selective reading mechanism that decides more accurately the extent to which each sentence in the model should be updated. Experimental results on the CNN/DailyMail and DUC2002 datasets demonstrate that our model significantly outperforms state-of-the-art extractive systems when evaluated by machines and by humans. |
Tasks | Extractive Document Summarization, Representation Learning, Text Summarization |
Published | 2018-09-27 |
URL | https://arxiv.org/abs/1809.10324v2 |
https://arxiv.org/pdf/1809.10324v2.pdf | |
PWC | https://paperswithcode.com/paper/iterative-document-representation-learning |
Repo | https://github.com/yingtaomj/Iterative-Document-Representation-Learning-Towards-Summarization-with-Polishing |
Framework | tf |
Unsupervised domain adaptation for medical imaging segmentation with self-ensembling
Title | Unsupervised domain adaptation for medical imaging segmentation with self-ensembling |
Authors | Christian S. Perone, Pedro Ballester, Rodrigo C. Barros, Julien Cohen-Adad |
Abstract | Recent advances in deep learning methods have come to define the state-of-the-art for many medical imaging applications, surpassing even human judgment in several tasks. Those models, however, when trained to reduce the empirical risk on a single domain, fail to generalize when applied to other domains, a very common scenario in medical imaging due to the variability of images and anatomical structures, even across the same imaging modality. In this work, we extend the method of unsupervised domain adaptation using self-ensembling for the semantic segmentation task and explore multiple facets of the method on a small and realistic publicly-available magnetic resonance (MRI) dataset. Through an extensive evaluation, we show that self-ensembling can indeed improve the generalization of the models even when using a small amount of unlabelled data. |
Tasks | Domain Adaptation, Medical Image Segmentation, Semantic Segmentation, Unsupervised Domain Adaptation |
Published | 2018-11-14 |
URL | http://arxiv.org/abs/1811.06042v2 |
http://arxiv.org/pdf/1811.06042v2.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-for-medical |
Repo | https://github.com/neuropoly/domainadaptation |
Framework | none |
Sparsity-based Defense against Adversarial Attacks on Linear Classifiers
Title | Sparsity-based Defense against Adversarial Attacks on Linear Classifiers |
Authors | Zhinus Marzi, Soorya Gopalakrishnan, Upamanyu Madhow, Ramtin Pedarsani |
Abstract | Deep neural networks represent the state of the art in machine learning in a growing number of fields, including vision, speech and natural language processing. However, recent work raises important questions about the robustness of such architectures, by showing that it is possible to induce classification errors through tiny, almost imperceptible, perturbations. Vulnerability to such “adversarial attacks”, or “adversarial examples”, has been conjectured to be due to the excessive linearity of deep networks. In this paper, we study this phenomenon in the setting of a linear classifier, and show that it is possible to exploit sparsity in natural data to combat $\ell_{\infty}$-bounded adversarial perturbations. Specifically, we demonstrate the efficacy of a sparsifying front end via an ensemble averaged analysis, and experimental results for the MNIST handwritten digit database. To the best of our knowledge, this is the first work to show that sparsity provides a theoretically rigorous framework for defense against adversarial attacks. |
Tasks | |
Published | 2018-01-15 |
URL | http://arxiv.org/abs/1801.04695v3 |
http://arxiv.org/pdf/1801.04695v3.pdf | |
PWC | https://paperswithcode.com/paper/sparsity-based-defense-against-adversarial |
Repo | https://github.com/ZhinusMarzi/Adversarial-attack |
Framework | tf |
Gated Fusion Network for Joint Image Deblurring and Super-Resolution
Title | Gated Fusion Network for Joint Image Deblurring and Super-Resolution |
Authors | Xinyi Zhang, Hang Dong, Zhe Hu, Wei-Sheng Lai, Fei Wang, Ming-Hsuan Yang |
Abstract | Single-image super-resolution is a fundamental task for vision applications to enhance the image quality with respect to spatial resolution. If the input image contains degraded pixels, the artifacts caused by the degradation could be amplified by super-resolution methods. Image blur is a common degradation source. Images captured by moving or still cameras are inevitably affected by motion blur due to relative movements between sensors and objects. In this work, we focus on the super-resolution task with the presence of motion blur. We propose a deep gated fusion convolution neural network to generate a clear high-resolution frame from a single natural image with severe blur. By decomposing the feature extraction step into two task-independent streams, the dual-branch design can facilitate the training process by avoiding learning the mixed degradation all-in-one and thus enhance the final high-resolution prediction results. Extensive experiments demonstrate that our method generates sharper super-resolved images from low-resolution inputs with high computational efficiency. |
Tasks | Deblurring, Image Super-Resolution, Super-Resolution |
Published | 2018-07-27 |
URL | http://arxiv.org/abs/1807.10806v1 |
http://arxiv.org/pdf/1807.10806v1.pdf | |
PWC | https://paperswithcode.com/paper/gated-fusion-network-for-joint-image |
Repo | https://github.com/jacquelinelala/GFN |
Framework | pytorch |
Multi-Task Handwritten Document Layout Analysis
Title | Multi-Task Handwritten Document Layout Analysis |
Authors | Lorenzo Quirós |
Abstract | Document Layout Analysis is a fundamental step in Handwritten Text Processing systems, from the extraction of the text lines to the type of zone it belongs to. We present a system based on artificial neural networks which is able to determine not only the baselines of text lines present in the document, but also performs geometric and logic layout analysis of the document. Experiments in three different datasets demonstrate the potential of the method and show competitive results with respect to state-of-the-art methods. |
Tasks | Document Layout Analysis |
Published | 2018-06-22 |
URL | http://arxiv.org/abs/1806.08852v3 |
http://arxiv.org/pdf/1806.08852v3.pdf | |
PWC | https://paperswithcode.com/paper/multi-task-handwritten-document-layout |
Repo | https://github.com/lquirosd/P2PaLA |
Framework | pytorch |
Graph Convolutional Neural Networks via Scattering
Title | Graph Convolutional Neural Networks via Scattering |
Authors | Dongmian Zou, Gilad Lerman |
Abstract | We generalize the scattering transform to graphs and consequently construct a convolutional neural network on graphs. We show that under certain conditions, any feature generated by such a network is approximately invariant to permutations and stable to graph manipulations. Numerical results demonstrate competitive performance on relevant datasets. |
Tasks | Node Classification |
Published | 2018-03-31 |
URL | http://arxiv.org/abs/1804.00099v2 |
http://arxiv.org/pdf/1804.00099v2.pdf | |
PWC | https://paperswithcode.com/paper/graph-convolutional-neural-networks-via-1 |
Repo | https://github.com/dmzou/SCAT |
Framework | tf |
Spartan Networks: Self-Feature-Squeezing Neural Networks for increased robustness in adversarial settings
Title | Spartan Networks: Self-Feature-Squeezing Neural Networks for increased robustness in adversarial settings |
Authors | François Menet, Paul Berthier, José M. Fernandez, Michel Gagnon |
Abstract | Deep learning models are vulnerable to adversarial examples which are input samples modified in order to maximize the error on the system. We introduce Spartan Networks, resistant deep neural networks that do not require input preprocessing nor adversarial training. These networks have an adversarial layer designed to discard some information of the network, thus forcing the system to focus on relevant input. This is done using a new activation function to discard data. The added layer trains the neural network to filter-out usually-irrelevant parts of its input. Our performance evaluation shows that Spartan Networks have a slightly lower precision but report a higher robustness under attack when compared to unprotected models. Results of this study of Adversarial AI as a new attack vector are based on tests conducted on the MNIST dataset. |
Tasks | |
Published | 2018-12-17 |
URL | http://arxiv.org/abs/1812.06815v1 |
http://arxiv.org/pdf/1812.06815v1.pdf | |
PWC | https://paperswithcode.com/paper/spartan-networks-self-feature-squeezing |
Repo | https://github.com/FMenet/Spartan-Networks |
Framework | tf |
Multimodal Continuous Turn-Taking Prediction Using Multiscale RNNs
Title | Multimodal Continuous Turn-Taking Prediction Using Multiscale RNNs |
Authors | Matthew Roddy, Gabriel Skantze, Naomi Harte |
Abstract | In human conversational interactions, turn-taking exchanges can be coordinated using cues from multiple modalities. To design spoken dialog systems that can conduct fluid interactions it is desirable to incorporate cues from separate modalities into turn-taking models. We propose that there is an appropriate temporal granularity at which modalities should be modeled. We design a multiscale RNN architecture to model modalities at separate timescales in a continuous manner. Our results show that modeling linguistic and acoustic features at separate temporal rates can be beneficial for turn-taking modeling. We also show that our approach can be used to incorporate gaze features into turn-taking models. |
Tasks | |
Published | 2018-08-31 |
URL | http://arxiv.org/abs/1808.10785v1 |
http://arxiv.org/pdf/1808.10785v1.pdf | |
PWC | https://paperswithcode.com/paper/multimodal-continuous-turn-taking-prediction |
Repo | https://github.com/mattroddy/lstm_turn_taking_prediction |
Framework | pytorch |
Italian Event Detection Goes Deep Learning
Title | Italian Event Detection Goes Deep Learning |
Authors | Tommaso Caselli |
Abstract | This paper reports on a set of experiments with different word embeddings to initialize a state-of-the-art Bi-LSTM-CRF network for event detection and classification in Italian, following the EVENTI evaluation exercise. The net- work obtains a new state-of-the-art result by improving the F1 score for detection of 1.3 points, and of 6.5 points for classification, by using a single step approach. The results also provide further evidence that embeddings have a major impact on the performance of such architectures. |
Tasks | Word Embeddings |
Published | 2018-10-04 |
URL | http://arxiv.org/abs/1810.02229v1 |
http://arxiv.org/pdf/1810.02229v1.pdf | |
PWC | https://paperswithcode.com/paper/italian-event-detection-goes-deep-learning |
Repo | https://github.com/tommasoc80/Event_detection_CLiC-it2018 |
Framework | none |
Macquarie University at BioASQ 6b: Deep learning and deep reinforcement learning for query-based multi-document summarisation
Title | Macquarie University at BioASQ 6b: Deep learning and deep reinforcement learning for query-based multi-document summarisation |
Authors | Diego Mollá |
Abstract | This paper describes Macquarie University’s contribution to the BioASQ Challenge (BioASQ 6b, Phase B). We focused on the extraction of the ideal answers, and the task was approached as an instance of query-based multi-document summarisation. In particular, this paper focuses on the experiments related to the deep learning and reinforcement learning approaches used in the submitted runs. The best run used a deep learning model under a regression-based framework. The deep learning architecture used features derived from the output of LSTM chains on word embeddings, plus features based on similarity with the query, and sentence position. The reinforcement learning approach was a proof-of-concept prototype that trained a global policy using REINFORCE. The global policy was implemented as a neural network that used $tf.idf$ features encoding the candidate sentence, question, and context. |
Tasks | Word Embeddings |
Published | 2018-09-14 |
URL | http://arxiv.org/abs/1809.05283v2 |
http://arxiv.org/pdf/1809.05283v2.pdf | |
PWC | https://paperswithcode.com/paper/macquarie-university-at-bioasq-6b-deep-1 |
Repo | https://github.com/dmollaaliod/bioasq6b-public |
Framework | none |
SciDTB: Discourse Dependency TreeBank for Scientific Abstracts
Title | SciDTB: Discourse Dependency TreeBank for Scientific Abstracts |
Authors | An Yang, Sujian Li |
Abstract | Annotation corpus for discourse relations benefits NLP tasks such as machine translation and question answering. In this paper, we present SciDTB, a domain-specific discourse treebank annotated on scientific articles. Different from widely-used RST-DT and PDTB, SciDTB uses dependency trees to represent discourse structure, which is flexible and simplified to some extent but do not sacrifice structural integrity. We discuss the labeling framework, annotation workflow and some statistics about SciDTB. Furthermore, our treebank is made as a benchmark for evaluating discourse dependency parsers, on which we provide several baselines as fundamental work. |
Tasks | Machine Translation, Question Answering |
Published | 2018-06-10 |
URL | http://arxiv.org/abs/1806.03653v1 |
http://arxiv.org/pdf/1806.03653v1.pdf | |
PWC | https://paperswithcode.com/paper/scidtb-discourse-dependency-treebank-for |
Repo | https://github.com/PKU-TANGENT/SciDTB |
Framework | none |
Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples
Title | Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples |
Authors | Vidur Joshi, Matthew Peters, Mark Hopkins |
Abstract | We revisit domain adaptation for parsers in the neural era. First we show that recent advances in word representations greatly diminish the need for domain adaptation when the target domain is syntactically similar to the source domain. As evidence, we train a parser on the Wall Street Jour- nal alone that achieves over 90% F1 on the Brown corpus. For more syntactically dis- tant domains, we provide a simple way to adapt a parser using only dozens of partial annotations. For instance, we increase the percentage of error-free geometry-domain parses in a held-out set from 45% to 73% using approximately five dozen training examples. In the process, we demon- strate a new state-of-the-art single model result on the Wall Street Journal test set of 94.3%. This is an absolute increase of 1.7% over the previous state-of-the-art of 92.6%. |
Tasks | Domain Adaptation |
Published | 2018-05-16 |
URL | http://arxiv.org/abs/1805.06556v1 |
http://arxiv.org/pdf/1805.06556v1.pdf | |
PWC | https://paperswithcode.com/paper/extending-a-parser-to-distant-domains-using-a |
Repo | https://github.com/vidurj/parser-adaptation |
Framework | pytorch |
End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
Title | End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion |
Authors | Chao Shang, Yun Tang, Jing Huang, Jinbo Bi, Xiaodong He, Bowen Zhou |
Abstract | Knowledge graph embedding has been an active research topic for knowledge base completion, with progressive improvement from the initial TransE, TransH, DistMult et al to the current state-of-the-art ConvE. ConvE uses 2D convolution over embeddings and multiple layers of nonlinear features to model knowledge graphs. The model can be efficiently trained and scalable to large knowledge graphs. However, there is no structure enforcement in the embedding space of ConvE. The recent graph convolutional network (GCN) provides another way of learning graph node embedding by successfully utilizing graph connectivity structure. In this work, we propose a novel end-to-end Structure-Aware Convolutional Network (SACN) that takes the benefit of GCN and ConvE together. SACN consists of an encoder of a weighted graph convolutional network (WGCN), and a decoder of a convolutional network called Conv-TransE. WGCN utilizes knowledge graph node structure, node attributes and edge relation types. It has learnable weights that adapt the amount of information from neighbors used in local aggregation, leading to more accurate embeddings of graph nodes. Node attributes in the graph are represented as additional nodes in the WGCN. The decoder Conv-TransE enables the state-of-the-art ConvE to be translational between entities and relations while keeps the same link prediction performance as ConvE. We demonstrate the effectiveness of the proposed SACN on standard FB15k-237 and WN18RR datasets, and it gives about 10% relative improvement over the state-of-the-art ConvE in terms of HITS@1, HITS@3 and HITS@10. |
Tasks | Graph Embedding, Knowledge Base Completion, Knowledge Graph Embedding, Knowledge Graphs, Link Prediction |
Published | 2018-11-11 |
URL | http://arxiv.org/abs/1811.04441v2 |
http://arxiv.org/pdf/1811.04441v2.pdf | |
PWC | https://paperswithcode.com/paper/end-to-end-structure-aware-convolutional |
Repo | https://github.com/JD-AI-Research-Silicon-Valley/SACN |
Framework | pytorch |
Denotation Extraction for Interactive Learning in Dialogue Systems
Title | Denotation Extraction for Interactive Learning in Dialogue Systems |
Authors | Miroslav Vodolán, Filip Jurčíček |
Abstract | This paper presents a novel task using real user data obtained in human-machine conversation. The task concerns with denotation extraction from answer hints collected interactively in a dialogue. The task is motivated by the need for large amounts of training data for question answering dialogue system development, where the data is often expensive and hard to collect. Being able to collect denotation interactively and directly from users, one could improve, for example, natural understanding components on-line and ease the collection of the training data. This paper also presents introductory results of evaluation of several denotation extraction models including attention-based neural network approaches. |
Tasks | Question Answering |
Published | 2018-01-09 |
URL | http://arxiv.org/abs/1801.02916v1 |
http://arxiv.org/pdf/1801.02916v1.pdf | |
PWC | https://paperswithcode.com/paper/denotation-extraction-for-interactive |
Repo | https://github.com/vodolan/DenotationIdentification |
Framework | none |