January 28, 2020

3276 words 16 mins read

Paper Group ANR 923

Endoscopic vs. volumetric OCT imaging of mastoid bone structure for pose estimation in minimally invasive cochlear implant surgery. Deep K-SVD Denoising. Genetic Programming Hyper-Heuristics with Vehicle Collaboration for Uncertain Capacitated Arc Routing Problems. Learning Fair and Interpretable Representations via Linear Orthogonalization. Model …

Endoscopic vs. volumetric OCT imaging of mastoid bone structure for pose estimation in minimally invasive cochlear implant surgery


Title	Endoscopic vs. volumetric OCT imaging of mastoid bone structure for pose estimation in minimally invasive cochlear implant surgery
Authors	Max-Heinrich Laves, Sarah Latus, Jan Bergmeier, Tobias Ortmaier, Lüder A. Kahrs, Alexander Schlaefer
Abstract	Purpose: The facial recess is a delicate structure that must be protected in minimally invasive cochlear implant surgery. Current research estimates the drill trajectory by using endoscopy of the unique mastoid patterns. However, missing depth information limits available features for a registration to preoperative CT data. Therefore, this paper evaluates OCT for enhanced imaging of drill holes in mastoid bone and compares OCT data to original endoscopic images. Methods: A catheter-based OCT probe is inserted into a drill trajectory of a mastoid phantom in a translation-rotation manner to acquire the inner surface state. The images are undistorted and stitched to create volumentric data of the drill hole. The mastoid cell pattern is segmented automatically and compared to ground truth. Results: The mastoid pattern segmented on images acquired with OCT show a similarity of J = 73.6 % to ground truth based on endoscopic images and measured with the Jaccard metric. Leveraged by additional depth information, automated segmentation tends to be more robust and fail-safe compared to endoscopic images. Conclusion: The feasibility of using a clinically approved OCT probe for imaging the drill hole in cochlear implantation is shown. The resulting volumentric images provide additional information on the shape of caveties in the bone structure, which will be useful for image-to-patient registration and to estimate the drill trajectory. This will be another step towards safe minimally invasive cochlear implantation.
Tasks	Pose Estimation
Published	2019-01-19
URL	http://arxiv.org/abs/1901.06490v2
PDF	http://arxiv.org/pdf/1901.06490v2.pdf
PWC	https://paperswithcode.com/paper/endoscopic-vs-volumetric-oct-imaging-of
Repo
Framework

Deep K-SVD Denoising


Title	Deep K-SVD Denoising
Authors	Meyer Scetbon, Michael Elad, Peyman Milanfar
Abstract	This work considers noise removal from images, focusing on the well known K-SVD denoising algorithm. This sparsity-based method was proposed in 2006, and for a short while it was considered as state-of-the-art. However, over the years it has been surpassed by other methods, including the recent deep-learning-based newcomers. The question we address in this paper is whether K-SVD was brought to its peak in its original conception, or whether it can be made competitive again. The approach we take in answering this question is to redesign the algorithm to operate in a supervised manner. More specifically, we propose an end-to-end deep architecture with the exact K-SVD computational path, and train it for optimized denoising. Our work shows how to overcome difficulties arising in turning the K-SVD scheme into a differentiable, and thus learnable, machine. With a small number of parameters to learn and while preserving the original K-SVD essence, the proposed architecture is shown to outperform the classical K-SVD algorithm substantially, and getting closer to recent state-of-the-art learning-based denoising methods. Adopting a broader context, this work touches on themes around the design of deep-learning solutions for image processing tasks, while paving a bridge between classic methods and novel deep-learning-based ones.
Tasks	Denoising
Published	2019-09-28
URL	https://arxiv.org/abs/1909.13164v1
PDF	https://arxiv.org/pdf/1909.13164v1.pdf
PWC	https://paperswithcode.com/paper/deep-k-svd-denoising
Repo
Framework

Genetic Programming Hyper-Heuristics with Vehicle Collaboration for Uncertain Capacitated Arc Routing Problems


Title	Genetic Programming Hyper-Heuristics with Vehicle Collaboration for Uncertain Capacitated Arc Routing Problems
Authors	Jordan MacLachlan, Yi Mei, Juergen Branke, Mengjie Zhang
Abstract	Due to its direct relevance to post-disaster operations, meter reading and civil refuse collection, the Uncertain Capacitated Arc Routing Problem (UCARP) is an important optimisation problem. Stochastic models are critical to study as they more accurately represent the real-world than their deterministic counterparts. Although there have been extensive studies in solving routing problems under uncertainty, very few have considered UCARP, and none consider collaboration between vehicles to handle the negative effects of uncertainty. This paper proposes a novel Solution Construction Procedure (SCP) that generates solutions to UCARP within a collaborative, multi-vehicle framework. It consists of two types of collaborative activities: one when a vehicle unexpectedly expends capacity (\emph{route failure}), and the other during the refill process. Then, we propose a Genetic Programming Hyper-Heuristic (GPHH) algorithm to evolve the routing policy used within the collaborative framework. The experimental studies show that the new heuristic with vehicle collaboration and GP-evolved routing policy significantly outperforms the compared state-of-the-art algorithms on commonly studied test problems. This is shown to be especially true on instances with larger numbers of tasks and vehicles. This clearly shows the advantage of vehicle collaboration in handling the uncertain environment, and the effectiveness of the newly proposed algorithm.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.08650v1
PDF	https://arxiv.org/pdf/1911.08650v1.pdf
PWC	https://paperswithcode.com/paper/genetic-programming-hyper-heuristics-with
Repo
Framework

Learning Fair and Interpretable Representations via Linear Orthogonalization


Title	Learning Fair and Interpretable Representations via Linear Orthogonalization
Authors	Yuzi He, Keith Burghardt, Kristina Lerman
Abstract	To reduce human error and prejudice, many high-stakes decisions have been turned over to machine algorithms. However, recent research suggests that this does not remove discrimination, and can perpetuate harmful stereotypes. While algorithms have been developed to improve fairness, they typically face at least one of three shortcomings: they are not interpretable, their prediction quality deteriorates quickly compared to unbiased equivalents, and they are not easily transferable across models. To address these shortcomings, we propose a geometric method that removes correlations between data and any number of protected variables. Further, we can control the strength of debiasing through an adjustable parameter to address the trade-off between prediction quality and fairness. The resulting features are interpretable and can be used with many popular models, such as linear regression, random forest, and multilayer perceptrons. The resulting predictions are found to be more accurate and fair compared to several state-of-the-art fair AI algorithms across a variety of benchmark datasets. Our work shows that debiasing data is a simple and effective solution toward improving fairness.
Tasks
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12854v2
PDF	https://arxiv.org/pdf/1910.12854v2.pdf
PWC	https://paperswithcode.com/paper/learning-fair-and-interpretable
Repo
Framework

Model Weight Theft With Just Noise Inputs: The Curious Case of the Petulant Attacker


Title	Model Weight Theft With Just Noise Inputs: The Curious Case of the Petulant Attacker
Authors	Nicholas Roberts, Vinay Uday Prabhu, Matthew McAteer
Abstract	This paper explores the scenarios under which an attacker can claim that ‘Noise and access to the softmax layer of the model is all you need’ to steal the weights of a convolutional neural network whose architecture is already known. We were able to achieve 96% test accuracy using the stolen MNIST model and 82% accuracy using the stolen KMNIST model learned using only i.i.d. Bernoulli noise inputs. We posit that this theft-susceptibility of the weights is indicative of the complexity of the dataset and propose a new metric that captures the same. The goal of this dissemination is to not just showcase how far knowing the architecture can take you in terms of model stealing, but to also draw attention to this rather idiosyncratic weight learnability aspects of CNNs spurred by i.i.d. noise input. We also disseminate some initial results obtained with using the Ising probability distribution in lieu of the i.i.d. Bernoulli distribution.
Tasks
Published	2019-12-19
URL	https://arxiv.org/abs/1912.08987v1
PDF	https://arxiv.org/pdf/1912.08987v1.pdf
PWC	https://paperswithcode.com/paper/model-weight-theft-with-just-noise-inputs-the
Repo
Framework

Particle Swarm Optimisation for Evolving Deep Neural Networks for Image Classification by Evolving and Stacking Transferable Blocks


Title	Particle Swarm Optimisation for Evolving Deep Neural Networks for Image Classification by Evolving and Stacking Transferable Blocks
Authors	Bin Wang, Bing Xue, Mengjie Zhang
Abstract	Deep Convolutional Neural Networks (CNNs) have been widely used in image classification tasks, but the process of designing CNN architectures is very complex, so Neural Architecture Search (NAS), automatically searching for optimal CNN architectures, has attracted more and more research interests. However, the computational cost of NAS is often too high to apply NAS on real-life applications. In this paper, an efficient particle swarm optimisation method named EPSOCNN is proposed to evolve CNN architectures inspired by the idea of transfer learning. EPSOCNN successfully reduces the computation cost by minimising the search space to a single block and utilising a small subset of the training set to evaluate CNNs during evolutionary process. Meanwhile, EPSOCNN also keeps very competitive classification accuracy by stacking the evolved block multiple times to fit the whole dataset. The proposed EPSOCNN algorithm is evaluated on CIFAR-10 dataset and compared with 13 peer competitors comprised of deep CNNs crafted by hand, learned by reinforcement learning methods and evolved by evolutionary computation approaches, which shows very promising results by outperforming all of the peer competitors with regard to the classification accuracy, number of parameters and the computational cost.
Tasks	Image Classification, Neural Architecture Search, Transfer Learning
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12659v2
PDF	https://arxiv.org/pdf/1907.12659v2.pdf
PWC	https://paperswithcode.com/paper/particle-swarm-optimisation-for-evolving-deep
Repo
Framework

SAMM Long Videos: A Spontaneous Facial Micro- and Macro-Expressions Dataset


Title	SAMM Long Videos: A Spontaneous Facial Micro- and Macro-Expressions Dataset
Authors	Chuin Hong Yap, Connah Kendrick, Moi Hoon Yap
Abstract	With the growth of popularity of facial micro-expressions in recent years, the demand for long videos with micro- and macro-expressions remains high. Extended from SAMM, a micro-expressions dataset released in 2016, this paper presents SAMM Long Videos dataset for spontaneous micro- and macro-expressions recognition and spotting. SAMM Long Videos dataset consists of 147 long videos with 343 macro-expressions and 159 micro-expressions. The dataset is FACS-coded with detailed Action Units (AUs). We compare our dataset with Chinese Academy of Sciences Macro-Expressions and Micro-Expressions (CAS(ME)2) dataset, which is the only available fully annotated dataset with micro- and macro-expressions. Furthermore, we preprocess the long videos using OpenFace, which includes face alignment and detection of facial AUs. We conduct facial expression spotting using this dataset and compare it with the baseline of MEGC III. Our spotting method outperformed the baseline result with F1-score of 0.3299.
Tasks	Face Alignment
Published	2019-11-04
URL	https://arxiv.org/abs/1911.01519v2
PDF	https://arxiv.org/pdf/1911.01519v2.pdf
PWC	https://paperswithcode.com/paper/samm-long-videos-a-spontaneous-facial-micro
Repo
Framework

Binary Classification with Bounded Abstention Rate


Title	Binary Classification with Bounded Abstention Rate
Authors	Shubhanshu Shekhar, Mohammad Ghavamzadeh, Tara Javidi
Abstract	We consider the problem of binary classification with abstention in the relatively less studied \emph{bounded-rate} setting. We begin by obtaining a characterization of the Bayes optimal classifier for an arbitrary input-label distribution $P_{XY}$. Our result generalizes and provides an alternative proof for the result first obtained by \cite{chow1957optimum}, and then re-derived by \citet{denis2015consistency}, under a continuity assumption on $P_{XY}$. We then propose a plug-in classifier that employs unlabeled samples to decide the region of abstention and derive an upper-bound on the excess risk of our classifier under standard \emph{H"older smoothness} and \emph{margin} assumptions. Unlike the plug-in rule of \citet{denis2015consistency}, our constructed classifier satisfies the abstention constraint with high probability and can also deal with discontinuities in the empirical cdf. We also derive lower-bounds that demonstrate the minimax near-optimality of our proposed algorithm. To address the excessive complexity of the plug-in classifier in high dimensions, we propose a computationally efficient algorithm that builds upon prior work on convex loss surrogates, and obtain bounds on its excess risk in the \emph{realizable} case. We empirically compare the performance of the proposed algorithm with a baseline on a number of UCI benchmark datasets.
Tasks
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09561v1
PDF	https://arxiv.org/pdf/1905.09561v1.pdf
PWC	https://paperswithcode.com/paper/binary-classification-with-bounded-abstention
Repo
Framework

Multi-Band Multi-Resolution Fully Convolutional Neural Networks for Singing Voice Separation


Title	Multi-Band Multi-Resolution Fully Convolutional Neural Networks for Singing Voice Separation
Authors	Emad M. Grais, Fei Zhao, Mark D. Plumbley
Abstract	Deep neural networks with convolutional layers usually process the entire spectrogram of an audio signal with the same time-frequency resolutions, number of filters, and dimensionality reduction scale. According to the constant-Q transform, good features can be extracted from audio signals if the low frequency bands are processed with high frequency resolution filters and the high frequency bands with high time resolution filters. In the spectrogram of a mixture of singing voices and music signals, there is usually more information about the voice in the low frequency bands than the high frequency bands. These raise the need for processing each part of the spectrogram differently. In this paper, we propose a multi-band multi-resolution fully convolutional neural network (MBR-FCN) for singing voice separation. The MBR-FCN processes the frequency bands that have more information about the target signals with more filters and smaller dimentionality reduction scale than the bands with less information. Furthermore, the MBR-FCN processes the low frequency bands with high frequency resolution filters and the high frequency bands with high time resolution filters. Our experimental results show that the proposed MBR-FCN with very few parameters achieves better singing voice separation performance than other deep neural networks.
Tasks	Dimensionality Reduction
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09266v1
PDF	https://arxiv.org/pdf/1910.09266v1.pdf
PWC	https://paperswithcode.com/paper/multi-band-multi-resolution-fully
Repo
Framework

TexTrolls: Identifying Russian Trolls on Twitter from a Textual Perspective


Title	TexTrolls: Identifying Russian Trolls on Twitter from a Textual Perspective
Authors	Bilal Ghanem, Davide Buscaldi, Paolo Rosso
Abstract	The online new emerging suspicious users, that usually are called trolls, are one of the main sources of hate, fake, and deceptive online messages. Some agendas are utilizing these harmful users to spread incitement tweets, and as a consequence, the audience get deceived. The challenge in detecting such accounts is that they conceal their identities which make them disguised in social media, adding more difficulty to identify them using just their social network information. Therefore, in this paper, we propose a text-based approach to detect the online trolls such as those that were discovered during the US 2016 presidential elections. Our approach is mainly based on textual features which utilize thematic information, and profiling features to identify the accounts from their way of writing tweets. We deduced the thematic information in a unsupervised way and we show that coupling them with the textual features enhanced the performance of the proposed model. In addition, we find that the proposed profiling features perform the best comparing to the textual features.
Tasks
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01340v1
PDF	https://arxiv.org/pdf/1910.01340v1.pdf
PWC	https://paperswithcode.com/paper/textrolls-identifying-russian-trolls-on
Repo
Framework

Surrogate Models for Enhancing the Efficiency of Neuroevolution in Reinforcement Learning


Title	Surrogate Models for Enhancing the Efficiency of Neuroevolution in Reinforcement Learning
Authors	Jörg Stork, Martin Zaefferer, Thomas Bartz-Beielstein, A. E. Eiben
Abstract	In the last years, reinforcement learning received a lot of attention. One method to solve reinforcement learning tasks is Neuroevolution, where neural networks are optimized by evolutionary algorithms. A disadvantage of Neuroevolution is that it can require numerous function evaluations, while not fully utilizing the available information from each fitness evaluation. This is especially problematic when fitness evaluations become expensive. To reduce the cost of fitness evaluations, surrogate models can be employed to partially replace the fitness function. The difficulty of surrogate modeling for Neuroevolution is the complex search space and how to compare different networks. To that end, recent studies showed that a kernel based approach, particular with phenotypic distance measures, works well. These kernels compare different networks via their behavior (phenotype) rather than their topology or encoding (genotype). In this work, we discuss the use of surrogate model-based Neuroevolution (SMB-NE) using a phenotypic distance for reinforcement learning. In detail, we investigate a) the potential of SMB-NE with respect to evaluation efficiency and b) how to select adequate input sets for the phenotypic distance measure in a reinforcement learning problem. The results indicate that we are able to considerably increase the evaluation efficiency using dynamic input sets.
Tasks
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09300v1
PDF	https://arxiv.org/pdf/1907.09300v1.pdf
PWC	https://paperswithcode.com/paper/surrogate-models-for-enhancing-the-efficiency
Repo
Framework

Improving Skip-Gram based Graph Embeddings via Centrality-Weighted Sampling


Title	Improving Skip-Gram based Graph Embeddings via Centrality-Weighted Sampling
Authors	Pedro Almagro-Blanco, Fernando Sancho-Caparrini
Abstract	Network embedding techniques inspired by word2vec represent an effective unsupervised relational learning model. Commonly, by means of a Skip-Gram procedure, these techniques learn low dimensional vector representations of the nodes in a graph by sampling node-context examples. Although many ways of sampling the context of a node have been proposed, the effects of the way a node is chosen have not been analyzed in depth. To fill this gap, we have re-implemented the main four word2vec inspired graph embedding techniques under the same framework and analyzed how different sampling distributions affects embeddings performance when tested in node classification problems. We present a set of experiments on different well known real data sets that show how the use of popular centrality distributions in sampling leads to improvements, obtaining speeds of up to 2 times in learning times and increasing accuracy in all cases.
Tasks	Graph Embedding, Network Embedding, Node Classification, Relational Reasoning
Published	2019-07-20
URL	https://arxiv.org/abs/1907.08793v1
PDF	https://arxiv.org/pdf/1907.08793v1.pdf
PWC	https://paperswithcode.com/paper/improving-skip-gram-based-graph-embeddings
Repo
Framework

Improving detection of protein-ligand binding sites with 3D segmentation


Title	Improving detection of protein-ligand binding sites with 3D segmentation
Authors	Marta M. Stepniewska-Dziubinska, Piotr Zielenkiewicz, Pawel Siedlecki
Abstract	In recent years machine learning (ML) took bio- and cheminformatics fields by storm, providing new solutions for a vast repertoire of problems related to protein sequence, structure, and interactions analysis. ML techniques, deep neural networks especially, were proven more effective than classical models for tasks like predicting binding affinity for molecular complex. In this work we investigated the earlier stage of drug discovery process - finding druggable pockets on protein surface, that can be later used to design active molecules. For this purpose we developed a 3D fully convolutional neural network capable of binding site segmentation. Our solution has high prediction accuracy and provides intuitive representations of the results, which makes it easy to incorporate into drug discovery projects. The model’s source code, together with scripts for most common use-cases is freely available at http://gitlab.com/cheminfIBB/kalasanty
Tasks	Drug Discovery
Published	2019-04-13
URL	https://arxiv.org/abs/1904.06517v2
PDF	https://arxiv.org/pdf/1904.06517v2.pdf
PWC	https://paperswithcode.com/paper/detection-of-protein-ligand-binding-sites
Repo
Framework

Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization


Title	Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization
Authors	Stefan Vlaski, Ali H. Sayed
Abstract	Recent years have seen increased interest in performance guarantees of gradient descent algorithms for non-convex optimization. A number of works have uncovered that gradient noise plays a critical role in the ability of gradient descent recursions to efficiently escape saddle-points and reach second-order stationary points. Most available works limit the gradient noise component to be bounded with probability one or sub-Gaussian and leverage concentration inequalities to arrive at high-probability results. We present an alternate approach, relying primarily on mean-square arguments and show that a more relaxed relative bound on the gradient noise variance is sufficient to ensure efficient escape from saddle-points without the need to inject additional noise, employ alternating step-sizes or rely on a global dispersive noise assumption, as long as a gradient noise component is present in a descent direction for every saddle-point.
Tasks
Published	2019-08-19
URL	https://arxiv.org/abs/1908.07023v1
PDF	https://arxiv.org/pdf/1908.07023v1.pdf
PWC	https://paperswithcode.com/paper/second-order-guarantees-of-stochastic
Repo
Framework

Dynamic Neural Network Decoupling


Title	Dynamic Neural Network Decoupling
Authors	Yuchao Li, Rongrong Ji, Shaohui Lin, Baochang Zhang, Chenqian Yan, Yongjian Wu, Feiyue Huang, Ling Shao
Abstract	Convolutional neural networks (CNNs) have achieved a superior performance by taking advantages of the complex network architectures and huge numbers of parameters, which however become uninterpretable and challenge their full potential to practical applications. Towards better understand the rationale behind the network decisions, we propose a novel architecture decoupling method, which dynamically discovers the hierarchical path consisting of activated filters for each input image. In particular, architecture controlling module is introduced in each layer to encode the network architecture and identify the activated filters corresponding to the specific input. Then, mutual information between architecture encoding and the attribute of input image is maximized to decouple the network architecture, and subsequently disentangles the filters by limiting the outputs of filter during training. Extensive experiments show that several merits have been achieved based on the proposed architecture decoupling, i.e., interpretation, acceleration and adversarial attacking.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01166v1
PDF	https://arxiv.org/pdf/1906.01166v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-neural-network-decoupling
Repo
Framework