January 31, 2020

3193 words 15 mins read

Paper Group ANR 86

AssemblyNet: A large ensemble of CNNs for 3D Whole Brain MRI Segmentation. Recent advances in conversational NLP : Towards the standardization of Chatbot building. Fairness risk measures. CompareNet: Anatomical Segmentation Network with Deep Non-local Label Fusion. FastSurfer – A fast and accurate deep learning based neuroimaging pipeline. Lifelon …

AssemblyNet: A large ensemble of CNNs for 3D Whole Brain MRI Segmentation


Title	AssemblyNet: A large ensemble of CNNs for 3D Whole Brain MRI Segmentation
Authors	Pierrick Coupé, Boris Mansencal, Michaël Clément, Rémi Giraud, Baudouin Denis de Senneville, Vinh-Thong Ta, Vincent Lepetit, José V. Manjon
Abstract	Whole brain segmentation using deep learning (DL) is a very challenging task since the number of anatomical labels is very high compared to the number of available training images. To address this problem, previous DL methods proposed to use a single convolution neural network (CNN) or few independent CNNs. In this paper, we present a novel ensemble method based on a large number of CNNs processing different overlapping brain areas. Inspired by parliamentary decision-making systems, we propose a framework called AssemblyNet, made of two “assemblies” of U-Nets. Such a parliamentary system is capable of dealing with complex decisions, unseen problem and reaching a consensus quickly. AssemblyNet introduces sharing of knowledge among neighboring U-Nets, an “amendment” procedure made by the second assembly at higher-resolution to refine the decision taken by the first one, and a final decision obtained by majority voting. During our validation, AssemblyNet showed competitive performance compared to state-of-the-art methods such as U-Net, Joint label fusion and SLANT. Moreover, we investigated the scan-rescan consistency and the robustness to disease effects of our method. These experiences demonstrated the reliability of AssemblyNet. Finally, we showed the interest of using semi-supervised learning to improve the performance of our method.
Tasks	Brain Segmentation, Decision Making
Published	2019-11-20
URL	https://arxiv.org/abs/1911.09098v1
PDF	https://arxiv.org/pdf/1911.09098v1.pdf
PWC	https://paperswithcode.com/paper/assemblynet-a-large-ensemble-of-cnns-for-3d
Repo
Framework

Recent advances in conversational NLP : Towards the standardization of Chatbot building


Title	Recent advances in conversational NLP : Towards the standardization of Chatbot building
Authors	Maali Mnasri
Abstract	Dialogue systems have become recently essential in our life. Their use is getting more and more fluid and easy throughout the time. This boils down to the improvements made in NLP and AI fields. In this paper, we try to provide an overview to the current state of the art of dialogue systems, their categories and the different approaches to build them. We end up with a discussion that compares all the techniques and analyzes the strengths and weaknesses of each. Finally, we present an opinion piece suggesting to orientate the research towards the standardization of dialogue systems building.
Tasks	Chatbot
Published	2019-03-21
URL	http://arxiv.org/abs/1903.09025v1
PDF	http://arxiv.org/pdf/1903.09025v1.pdf
PWC	https://paperswithcode.com/paper/recent-advances-in-conversational-nlp-towards
Repo
Framework

Fairness risk measures


Title	Fairness risk measures
Authors	Robert C. Williamson, Aditya Krishna Menon
Abstract	Ensuring that classifiers are non-discriminatory or fair with respect to a sensitive feature (e.g., race or gender) is a topical problem. Progress in this task requires fixing a definition of fairness, and there have been several proposals in this regard over the past few years. Several of these, however, assume either binary sensitive features (thus precluding categorical or real-valued sensitive groups), or result in non-convex objectives (thus adversely affecting the optimisation landscape). In this paper, we propose a new definition of fairness that generalises some existing proposals, while allowing for generic sensitive features and resulting in a convex objective. The key idea is to enforce that the expected losses (or risks) across each subgroup induced by the sensitive feature are commensurate. We show how this relates to the rich literature on risk measures from mathematical finance. As a special case, this leads to a new convex fairness-aware objective based on minimising the conditional value at risk (CVaR).
Tasks
Published	2019-01-24
URL	http://arxiv.org/abs/1901.08665v1
PDF	http://arxiv.org/pdf/1901.08665v1.pdf
PWC	https://paperswithcode.com/paper/fairness-risk-measures
Repo
Framework

CompareNet: Anatomical Segmentation Network with Deep Non-local Label Fusion


Title	CompareNet: Anatomical Segmentation Network with Deep Non-local Label Fusion
Authors	Yuan Liang, Weinan Song, J. P. Dym, Kun Wang, Lei He
Abstract	Label propagation is a popular technique for anatomical segmentation. In this work, we propose a novel deep framework for label propagation based on non-local label fusion. Our framework, named CompareNet, incorporates subnets for both extracting discriminating features, and learning the similarity measure, which lead to accurate segmentation. We also introduce the voxel-wise classification as an unary potential to the label fusion function, for alleviating the search failure issue of the existing non-local fusion strategies. Moreover, CompareNet is end-to-end trainable, and all the parameters are learnt together for the optimal performance. By evaluating CompareNet on two public datasets IBSRv2 and MICCAI 2012 for brain segmentation, we show it outperforms state-of-the-art methods in accuracy, while being robust to pathologies.
Tasks	Brain Segmentation
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04797v1
PDF	https://arxiv.org/pdf/1910.04797v1.pdf
PWC	https://paperswithcode.com/paper/comparenet-anatomical-segmentation-network
Repo
Framework

FastSurfer – A fast and accurate deep learning based neuroimaging pipeline


Title	FastSurfer – A fast and accurate deep learning based neuroimaging pipeline
Authors	Leonie Henschel, Sailesh Conjeti, Santiago Estrada, Kersten Diers, Bruce Fischl, Martin Reuter
Abstract	Traditional neuroimage analysis pipelines involve computationally intensive, time-consuming optimization steps, and thus, do not scale well to large cohort studies with thousands or tens of thousands of individuals. In this work we propose a fast and accurate deep learning based neuroimaging pipeline for the automated processing of structural human brain MRI scans, including surface reconstruction and cortical parcellation. To this end, we introduce an advanced deep learning architecture capable of whole brain segmentation into 95 classes in under 1 minute, mimicking FreeSurfer’s anatomical segmentation and cortical parcellation. The network architecture incorporates local and global competition via competitive dense blocks and competitive skip pathways, as well as multi-slice information aggregation that specifically tailor network performance towards accurate segmentation of both cortical and sub-cortical structures. Further, we perform fast cortical surface reconstruction and thickness analysis by introducing a spectral spherical embedding and by directly mapping the cortical labels from the image to the surface. This approach provides a full FreeSurfer alternative for volumetric analysis (within 1 minute) and surface-based thickness analysis (within only around 1h runtime). For sustainability of this approach we perform extensive validation: we assert high segmentation accuracy on several unseen datasets, measure generalizability and demonstrate increased test-retest reliability, and increased sensitivity to disease effects relative to traditional FreeSurfer.
Tasks	Brain Segmentation
Published	2019-10-09
URL	https://arxiv.org/abs/1910.03866v2
PDF	https://arxiv.org/pdf/1910.03866v2.pdf
PWC	https://paperswithcode.com/paper/fastsurfer-a-fast-and-accurate-deep-learning
Repo
Framework

Lifelong Spectral Clustering


Title	Lifelong Spectral Clustering
Authors	Gan Sun, Yang Cong, Qianqian Wang, Jun Li, Yun Fu
Abstract	In the past decades, spectral clustering (SC) has become one of the most effective clustering algorithms. However, most previous studies focus on spectral clustering tasks with a fixed task set, which cannot incorporate with a new spectral clustering task without accessing to previously learned tasks. In this paper, we aim to explore the problem of spectral clustering in a lifelong machine learning framework, i.e., Lifelong Spectral Clustering (L2SC). Its goal is to efficiently learn a model for a new spectral clustering task by selectively transferring previously accumulated experience from knowledge library. Specifically, the knowledge library of L2SC contains two components: 1) orthogonal basis library: capturing latent cluster centers among the clusters in each pair of tasks; 2) feature embedding library: embedding the feature manifold information shared among multiple related tasks. As a new spectral clustering task arrives, L2SC firstly transfers knowledge from both basis library and feature library to obtain encoding matrix, and further redefines the library base over time to maximize performance across all the clustering tasks. Meanwhile, a general online update formulation is derived to alternatively update the basis library and feature library. Finally, the empirical experiments on several real-world benchmark datasets demonstrate that our L2SC model can effectively improve the clustering performance when comparing with other state-of-the-art spectral clustering algorithms.
Tasks
Published	2019-11-27
URL	https://arxiv.org/abs/1911.11908v2
PDF	https://arxiv.org/pdf/1911.11908v2.pdf
PWC	https://paperswithcode.com/paper/lifelong-spectral-clustering
Repo
Framework

ASNI: Adaptive Structured Noise Injection for shallow and deep neural networks


Title	ASNI: Adaptive Structured Noise Injection for shallow and deep neural networks
Authors	Beyrem Khalfaoui, Joseph Boyd, Jean-Philippe Vert
Abstract	Dropout is a regularisation technique in neural network training where unit activations are randomly set to zero with a given probability \emph{independently}. In this work, we propose a generalisation of dropout and other multiplicative noise injection schemes for shallow and deep neural networks, where the random noise applied to different units is not independent but follows a joint distribution that is either fixed or estimated during training. We provide theoretical insights on why such adaptive structured noise injection (ASNI) may be relevant, and empirically confirm that it helps boost the accuracy of simple feedforward and convolutional neural networks, disentangles the hidden layer representations, and leads to sparser representations. Our proposed method is a straightforward modification of the classical dropout and does not require additional computational overhead.
Tasks
Published	2019-09-21
URL	https://arxiv.org/abs/1909.09819v1
PDF	https://arxiv.org/pdf/1909.09819v1.pdf
PWC	https://paperswithcode.com/paper/190909819
Repo
Framework

Sparsity through evolutionary pruning prevents neuronal networks from overfitting


Title	Sparsity through evolutionary pruning prevents neuronal networks from overfitting
Authors	Richard C. Gerum, André Erpenbeck, Patrick Krauss, Achim Schilling
Abstract	Modern Machine learning techniques take advantage of the exponentially rising calculation power in new generation processor units. Thus, the number of parameters which are trained to resolve complex tasks was highly increased over the last decades. However, still the networks fail - in contrast to our brain - to develop general intelligence in the sense of being able to solve several complex tasks with only one network architecture. This could be the case because the brain is not a randomly initialized neural network, which has to be trained by simply investing a lot of calculation power, but has from birth some fixed hierarchical structure. To make progress in decoding the structural basis of biological neural networks we here chose a bottom-up approach, where we evolutionarily trained small neural networks in performing a maze task. This simple maze task requires dynamical decision making with delayed rewards. We were able to show that during the evolutionary optimization random severance of connections lead to better generalization performance of the networks compared to fully connected networks. We conclude that sparsity is a central property of neural networks and should be considered for modern Machine learning approaches.
Tasks	Decision Making
Published	2019-11-07
URL	https://arxiv.org/abs/1911.10988v2
PDF	https://arxiv.org/pdf/1911.10988v2.pdf
PWC	https://paperswithcode.com/paper/sparsity-through-evolutionary-pruning
Repo
Framework

Learning Bayesian Networks with Low Rank Conditional Probability Tables


Title	Learning Bayesian Networks with Low Rank Conditional Probability Tables
Authors	Adarsh Barik, Jean Honorio
Abstract	In this paper, we provide a method to learn the directed structure of a Bayesian network using data. The data is accessed by making conditional probability queries to a black-box model. We introduce a notion of simplicity of representation of conditional probability tables for the nodes in the Bayesian network, that we call “low rankness”. We connect this notion to the Fourier transformation of real valued set functions and propose a method which learns the exact directed structure of a `low rank` Bayesian network using very few queries. We formally prove that our method correctly recovers the true directed structure, runs in polynomial time and only needs polynomial samples with respect to the number of nodes. We also provide further improvements in efficiency if we have access to some observational data.
Tasks
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12552v1
PDF	https://arxiv.org/pdf/1905.12552v1.pdf
PWC	https://paperswithcode.com/paper/learning-bayesian-networks-with-low-rank
Repo
Framework

Accurate Uncertainty Estimation and Decomposition in Ensemble Learning


Title	Accurate Uncertainty Estimation and Decomposition in Ensemble Learning
Authors	Jeremiah Zhe Liu, John Paisley, Marianthi-Anna Kioumourtzoglou, Brent Coull
Abstract	Ensemble learning is a standard approach to building machine learning systems that capture complex phenomena in real-world data. An important aspect of these systems is the complete and valid quantification of model uncertainty. We introduce a Bayesian nonparametric ensemble (BNE) approach that augments an existing ensemble model to account for different sources of model uncertainty. BNE augments a model’s prediction and distribution functions using Bayesian nonparametric machinery. It has a theoretical guarantee in that it robustly estimates the uncertainty patterns in the data distribution, and can decompose its overall predictive uncertainty into distinct components that are due to different sources of noise and error. We show that our method achieves accurate uncertainty estimates under complex observational noise, and illustrate its real-world utility in terms of uncertainty decomposition and model bias detection for an ensemble in predict air pollution exposures in Eastern Massachusetts, USA.
Tasks
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04061v1
PDF	https://arxiv.org/pdf/1911.04061v1.pdf
PWC	https://paperswithcode.com/paper/accurate-uncertainty-estimation-and
Repo
Framework

Automated Assignment of Backbone Resonances Using Residual Dipolar Couplings Acquired from a Protein with Known Structure


Title	Automated Assignment of Backbone Resonances Using Residual Dipolar Couplings Acquired from a Protein with Known Structure
Authors	P. Shealy, R. Mukhopadhyay, S. Smith, H. Valafar
Abstract	Resonance assignment is a critical first step in the investigation of protein structures using NMR spectroscopy. The development of assignment methods that require less experimental data is possible with prior knowledge of the macromolecular structure. Automated methods of performing the task of resonance assignment can significantly reduce the financial cost and time requirement for protein structure determination. Such methods can also be beneficial in validating a protein’s solution state structure. Here we present a new approach to the assignment problem. Our approach uses only RDC data to assign backbone resonances. It provides simultaneous order tensor estimation and assignment. Our approach compares independent order tensor estimates to determine when the correct order tensor has been found. We demonstrate the algorithm’s viability using simulated data from the protein domain 1A1Z.
Tasks
Published	2019-11-01
URL	https://arxiv.org/abs/1911.00526v1
PDF	https://arxiv.org/pdf/1911.00526v1.pdf
PWC	https://paperswithcode.com/paper/automated-assignment-of-backbone-resonances
Repo
Framework

Collaborative Data Acquisition


Title	Collaborative Data Acquisition
Authors	Wen Zhang, Yao Zhang, Dengji Zhao
Abstract	We consider a requester who acquires a set of data (e.g. images) that is not owned by one party. In order to collect as many data as possible, crowdsourcing mechanisms have been widely used to seek help from the crowd. However, existing mechanisms rely on third-party platforms, and the workers from these platforms are not necessarily helpful and redundant data are also not properly handled. To combat this problem, we propose a novel crowdsourcing mechanism based on social networks, where the rewards of the workers are calculated by information entropy and a modified Shapley value. This mechanism incentivizes the workers from the network to not only provide all data they have but also further invite their neighbours to offer more data. Eventually, the mechanism is able to acquire all data from all workers on the network and the requester’s cost is no more than the value of the data acquired. The experiments show that our mechanism outperforms traditional crowdsourcing mechanisms.
Tasks
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05481v2
PDF	https://arxiv.org/pdf/1905.05481v2.pdf
PWC	https://paperswithcode.com/paper/crowdsourcing-data-acquisition-via-social
Repo
Framework

Feature Selection for Better Spectral Characterization or: How I Learned to Start Worrying and Love Ensembles


Title	Feature Selection for Better Spectral Characterization or: How I Learned to Start Worrying and Love Ensembles
Authors	Sankalp Gilda
Abstract	An ever-looming threat to astronomical applications of machine learning is the danger of over-fitting data, also known as the `curse of dimensionality.’ This occurs when there are fewer samples than the number of independent variables. In this work, we focus on the problem of stellar parameterization from low-mid resolution spectra, with blended absorption lines. We address this problem using an iterative algorithm to sequentially prune redundant features from synthetic PHOENIX spectra, and arrive at an optimal set of wavelengths with the strongest correlation with each of the output variables – T$_{\rm eff}$, $\log g$, and [Fe/H]. We find that at any given resolution, most features (i.e., absorption lines) are not only redundant, but actually act as noise and decrease the accuracy of parameter retrieval. \|
Tasks	Feature Selection
Published	2019-02-19
URL	http://arxiv.org/abs/1902.07215v2
PDF	http://arxiv.org/pdf/1902.07215v2.pdf
PWC	https://paperswithcode.com/paper/feature-selection-for-better-spectral
Repo
Framework

Generalizing Deep Whole Brain Segmentation for Pediatric and Post-Contrast MRI with Augmented Transfer Learning


Title	Generalizing Deep Whole Brain Segmentation for Pediatric and Post-Contrast MRI with Augmented Transfer Learning
Authors	Camilo Bermudez, Justin Blaber, Samuel W. Remedios, Jess E. Reynolds, Catherine Lebel, Maureen McHugo, Stephan Heckers, Yuankai Huo, Bennett A. Landman
Abstract	Generalizability is an important problem in deep neural networks, especially in the context of the variability of data acquisition in clinical magnetic resonance imaging (MRI). Recently, the Spatially Localized Atlas Network Tiles (SLANT) approach has been shown to effectively segment whole brain non-contrast T1w MRI with 132 volumetric labels. Enhancing generalizability of SLANT would enable broader application of volumetric assessment in multi-site studies. Transfer learning (TL) is commonly used to update the neural network weights for local factors; yet, it is commonly recognized to risk degradation of performance on the original validation/test cohorts. Here, we explore TL by data augmentation to address these concerns in the context of adapting SLANT to anatomical variation and scanning protocol. We consider two datasets: First, we optimize for age with 30 T1w MRI of young children with manually corrected volumetric labels, and accuracy of automated segmentation defined relative to the manually provided truth. Second, we optimize for acquisition with 36 paired datasets of pre- and post-contrast clinically acquired T1w MRI, and accuracy of the post-contrast segmentations assessed relative to the pre-contrast automated assessment. For both studies, we augment the original TL step of SLANT with either only the new data or with both original and new data. Over baseline SLANT, both approaches yielded significantly improved performance (signed rank tests; pediatric: 0.89 vs. 0.82 DSC, p<0.001; contrast: 0.80 vs 0.76, p<0.001). The performance on the original test set decreased with the new-data only transfer learning approach, so data augmentation was superior to strict transfer learning.
Tasks	Brain Segmentation, Data Augmentation, Transfer Learning
Published	2019-08-13
URL	https://arxiv.org/abs/1908.04702v1
PDF	https://arxiv.org/pdf/1908.04702v1.pdf
PWC	https://paperswithcode.com/paper/generalizing-deep-whole-brain-segmentation
Repo
Framework

Deep-learning-based classification and retrieval of components of a process plant from segmented point clouds


Title	Deep-learning-based classification and retrieval of components of a process plant from segmented point clouds
Authors	Hyungki Kim, Duhwan Mun
Abstract	Technology to recognize the type of component represented by a point cloud is required in the reconstruction process of an as-built model of a process plant based on laser scanning. The reconstruction process of a process plant through laser scanning is divided into point cloud registration, point cloud segmentation, and component type recognition and placement. Loss of shape data or imbalance of point cloud density problems generally occur in the point cloud data collected from large-scale facilities. In this study, we experimented with the possibility of applying object recognition technology based on 3D deep learning networks, which have been showing high performance recently, and analyzed the results. For training data, we used a segmented point cloud repository about components that we constructed by scanning a process plant. For networks, we selected the multi-view convolutional neural network (MVCNN), which is a view-based method, and PointNet, which is designed to allow the direct input of point cloud data. In the case of the MVCNN, we also performed an experiment on the generation method for two types of multi-view images that can complement the shape occlusion of the segmented point cloud. In this experiment, the MVCNN showed the highest retrieval accuracy of approximately 87%, whereas PointNet showed the highest retrieval mean average precision of approximately 84%. Furthermore, both networks showed high recognition performance for the segmented point cloud of plant components when there was sufficient training data.
Tasks	Object Recognition, Point Cloud Registration
Published	2019-12-13
URL	https://arxiv.org/abs/1912.12135v1
PDF	https://arxiv.org/pdf/1912.12135v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-classification-and
Repo
Framework