April 3, 2020

2803 words 14 mins read

Paper Group ANR 7

3DPIFCM Novel Algorithm for Segmentation of Noisy Brain MRI Images. Fast and robust multiplane single molecule localization microscopy using deep neural network. MPM: Joint Representation of Motion and Position Map for Cell Tracking. The Pragmatic Turn in Explainable Artificial Intelligence (XAI). Confidence Scores Make Instance-dependent Label-noi …

3DPIFCM Novel Algorithm for Segmentation of Noisy Brain MRI Images


Title	3DPIFCM Novel Algorithm for Segmentation of Noisy Brain MRI Images
Authors	Arie Agranonik, Maya Herman, Mark Last
Abstract	We present a novel algorithm named 3DPIFCM, for automatic segmentation of noisy MRI Brain images. The algorithm is an extension of a well-known IFCM (Improved Fuzzy C-Means) algorithm. It performs fuzzy segmentation and introduces a fitness function that is affected by proximity of the voxels and by the color intensity in 3D images. The 3DPIFCM algorithm uses PSO (Particle Swarm Optimization) in order to optimize the fitness function. In addition, the 3DPIFCM uses 3D features of near voxels to better adjust the noisy artifacts. In our experiments, we evaluate 3DPIFCM on T1 Brainweb dataset with noise levels ranging from 1% to 20% and on a synthetic dataset with ground truth both in 3D. The analysis of the segmentation results shows a significant improvement in the segmentation quality of up to 28% compared to two generic variants in noisy images and up to 60% when compared to the original FCM (Fuzzy C-Means).
Tasks
Published	2020-02-05
URL	https://arxiv.org/abs/2002.01985v2
PDF	https://arxiv.org/pdf/2002.01985v2.pdf
PWC	https://paperswithcode.com/paper/3dpifcm-segmentation-algorithm-for-brain-mri
Repo
Framework

Fast and robust multiplane single molecule localization microscopy using deep neural network


Title	Fast and robust multiplane single molecule localization microscopy using deep neural network
Authors	Toshimitsu Aritake, Hideitsu Hino, Shigeyuki Namiki, Daisuke Asanuma, Kenzo Hirose, Noboru Murata
Abstract	Single molecule localization microscopy is widely used in biological research for measuring the nanostructures of samples smaller than the diffraction limit. This study uses multifocal plane microscopy and addresses the 3D single molecule localization problem, where lateral and axial locations of molecules are estimated. However, when we multifocal plane microscopy is used, the estimation accuracy of 3D localization is easily deteriorated by the small lateral drifts of camera positions. We formulate a 3D molecule localization problem along with the estimation of the lateral drifts as a compressed sensing problem, A deep neural network was applied to accurately and efficiently solve this problem. The proposed method is robust to the lateral drifts and achieves an accuracy of 20 nm laterally and 50 nm axially without an explicit drift correction.
Tasks
Published	2020-01-07
URL	https://arxiv.org/abs/2001.01893v1
PDF	https://arxiv.org/pdf/2001.01893v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-robust-multiplane-single-molecule
Repo
Framework

MPM: Joint Representation of Motion and Position Map for Cell Tracking


Title	MPM: Joint Representation of Motion and Position Map for Cell Tracking
Authors	Junya Hayashida, Kazuya Nishimura, Ryoma Bise
Abstract	Conventional cell tracking methods detect multiple cells in each frame (detection) and then associate the detection results in successive time-frames (association). Most cell tracking methods perform the association task independently from the detection task. However, there is no guarantee of preserving coherence between these tasks, and lack of coherence may adversely affect tracking performance. In this paper, we propose the Motion and Position Map (MPM) that jointly represents both detection and association for not only migration but also cell division. It guarantees coherence such that if a cell is detected, the corresponding motion flow can always be obtained. It is a simple but powerful method for multi-object tracking in dense environments. We compared the proposed method with current tracking methods under various conditions in real biological images and found that it outperformed the state-of-the-art (+5.2% improvement compared to the second-best).
Tasks	Multi-Object Tracking, Object Tracking
Published	2020-02-25
URL	https://arxiv.org/abs/2002.10749v2
PDF	https://arxiv.org/pdf/2002.10749v2.pdf
PWC	https://paperswithcode.com/paper/mpm-joint-representation-of-motion-and
Repo
Framework

The Pragmatic Turn in Explainable Artificial Intelligence (XAI)


Title	The Pragmatic Turn in Explainable Artificial Intelligence (XAI)
Authors	Andrés Páez
Abstract	In this paper I argue that the search for explainable models and interpretable decisions in AI must be reformulated in terms of the broader project of offering a pragmatic and naturalistic account of understanding in AI. Intuitively, the purpose of providing an explanation of a model or a decision is to make it understandable to its stakeholders. But without a previous grasp of what it means to say that an agent understands a model or a decision, the explanatory strategies will lack a well-defined goal. Aside from providing a clearer objective for XAI, focusing on understanding also allows us to relax the factivity condition on explanation, which is impossible to fulfill in many machine learning models, and to focus instead on the pragmatic conditions that determine the best fit between a model and the methods and devices deployed to understand it. After an examination of the different types of understanding discussed in the philosophical and psychological literature, I conclude that interpretative or approximation models not only provide the best way to achieve the objectual understanding of a machine learning model, but are also a necessary condition to achieve post-hoc interpretability. This conclusion is partly based on the shortcomings of the purely functionalist approach to post-hoc interpretability that seems to be predominant in most recent literature.
Tasks
Published	2020-02-22
URL	https://arxiv.org/abs/2002.09595v1
PDF	https://arxiv.org/pdf/2002.09595v1.pdf
PWC	https://paperswithcode.com/paper/the-pragmatic-turn-in-explainable-artificial
Repo
Framework

Confidence Scores Make Instance-dependent Label-noise Learning Possible


Title	Confidence Scores Make Instance-dependent Label-noise Learning Possible
Authors	Antonin Berthon, Bo Han, Gang Niu, Tongliang Liu, Masashi Sugiyama
Abstract	Learning with noisy labels has drawn a lot of attention. In this area, most of recent works only consider class-conditional noise, where the label noise is independent of its input features. This noise model may not be faithful to many real-world applications. Instead, few pioneer works have studied instance-dependent noise, but these methods are limited to strong assumptions on noise models. To alleviate this issue, we introduce confidence-scored instance-dependent noise (CSIDN), where each instance-label pair is associated with a confidence score. The confidence scores are sufficient to estimate the noise functions of each instance with minimal assumptions. Moreover, such scores can be easily and cheaply derived during the construction of the dataset through crowdsourcing or automatic annotation. To handle CSIDN, we design a benchmark algorithm termed instance-level forward correction. Empirical results on synthetic and real-world datasets demonstrate the utility of our proposed method.
Tasks
Published	2020-01-11
URL	https://arxiv.org/abs/2001.03772v1
PDF	https://arxiv.org/pdf/2001.03772v1.pdf
PWC	https://paperswithcode.com/paper/confidence-scores-make-instance-dependent-1
Repo
Framework

Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing


Title	Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing
Authors	Jinyuan Jia, Binghui Wang, Xiaoyu Cao, Neil Zhenqiang Gong
Abstract	Community detection plays a key role in understanding graph structure. However, several recent studies showed that community detection is vulnerable to adversarial structural perturbation. In particular, via adding or removing a small number of carefully selected edges in a graph, an attacker can manipulate the detected communities. However, to the best of our knowledge, there are no studies on certifying robustness of community detection against such adversarial structural perturbation. In this work, we aim to bridge this gap. Specifically, we develop the first certified robustness guarantee of community detection against adversarial structural perturbation. Given an arbitrary community detection method, we build a new smoothed community detection method via randomly perturbing the graph structure. We theoretically show that the smoothed community detection method provably groups a given arbitrary set of nodes into the same community (or different communities) when the number of edges added/removed by an attacker is bounded. Moreover, we show that our certified robustness is tight. We also empirically evaluate our method on multiple real-world graphs with ground truth communities.
Tasks	Community Detection
Published	2020-02-09
URL	https://arxiv.org/abs/2002.03421v1
PDF	https://arxiv.org/pdf/2002.03421v1.pdf
PWC	https://paperswithcode.com/paper/certified-robustness-of-community-detection
Repo
Framework

Explaining with Counter Visual Attributes and Examples


Title	Explaining with Counter Visual Attributes and Examples
Authors	Sadaf Gulshad, Arnold Smeulders
Abstract	In this paper, we aim to explain the decisions of neural networks by utilizing multimodal information. That is counter-intuitive attributes and counter visual examples which appear when perturbed samples are introduced. Different from previous work on interpreting decisions using saliency maps, text, or visual patches we propose to use attributes and counter-attributes, and examples and counter-examples as part of the visual explanations. When humans explain visual decisions they tend to do so by providing attributes and examples. Hence, inspired by the way of human explanations in this paper we provide attribute-based and example-based explanations. Moreover, humans also tend to explain their visual decisions by adding counter-attributes and counter-examples to explain what is not seen. We introduce directed perturbations in the examples to observe which attribute values change when classifying the examples into the counter classes. This delivers intuitive counter-attributes and counter-examples. Our experiments with both coarse and fine-grained datasets show that attributes provide discriminating and human-understandable intuitive and counter-intuitive explanations.
Tasks
Published	2020-01-27
URL	https://arxiv.org/abs/2001.09671v1
PDF	https://arxiv.org/pdf/2001.09671v1.pdf
PWC	https://paperswithcode.com/paper/explaining-with-counter-visual-attributes-and
Repo
Framework

Improving out-of-distribution generalization via multi-task self-supervised pretraining


Title	Improving out-of-distribution generalization via multi-task self-supervised pretraining
Authors	Isabela Albuquerque, Nikhil Naik, Junnan Li, Nitish Keskar, Richard Socher
Abstract	Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness. We show that features obtained using self-supervised learning are comparable to, or better than, supervised learning for domain generalization in computer vision. We introduce a new self-supervised pretext task of predicting responses to Gabor filter banks and demonstrate that multi-task learning of compatible pretext tasks improves domain generalization performance as compared to training individual tasks alone. Features learnt through self-supervision obtain better generalization to unseen domains when compared to their supervised counterpart when there is a larger domain shift between training and test distributions and even show better localization ability for objects of interest. Self-supervised feature representations can also be combined with other domain generalization methods to further boost performance.
Tasks	Domain Generalization, Few-Shot Learning, Multi-Task Learning
Published	2020-03-30
URL	https://arxiv.org/abs/2003.13525v1
PDF	https://arxiv.org/pdf/2003.13525v1.pdf
PWC	https://paperswithcode.com/paper/improving-out-of-distribution-generalization
Repo
Framework

Machine Learning Methods for Monitoring of Quasi-Periodic Traffic in Massive IoT Networks


Title	Machine Learning Methods for Monitoring of Quasi-Periodic Traffic in Massive IoT Networks
Authors	René Brandborg Sørensen, Jimmy Jessen Nielsen, Petar Popovski
Abstract	One of the central problems in massive Internet of Things (IoT) deployments is the monitoring of the status of a massive number of links. The problem is aggravated by the irregularity of the traffic transmitted over the link, as the traffic intermittency can be disguised as a link failure and vice versa. In this work we present a traffic model for IoT devices running quasi-periodic applications and we present both supervised and unsupervised machine learning methods for monitoring the network performance of IoT deployments with quasi-periodic reporting, such as smart-metering, environmental monitoring and agricultural monitoring. The unsupervised methods are based on the Lomb-Scargle periodogram, an approach developed by astronomers for estimating the spectral density of unevenly sampled time series.
Tasks	Time Series
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01552v2
PDF	https://arxiv.org/pdf/2002.01552v2.pdf
PWC	https://paperswithcode.com/paper/machine-learning-methods-for-monitoring-of
Repo
Framework

On the coexistence of competing languages


Title	On the coexistence of competing languages
Authors	Jean-Marc Luck, Anita Mehta
Abstract	We investigate the evolution of competing languages, a subject where much previous literature suggests that the outcome is always the domination of one language over all the others. Since coexistence of languages is observed in reality, we here revisit the question of language competition, with an emphasis on uncovering the ways in which coexistence might emerge. We find that this emergence is related to symmetry breaking, and explore two particular scenarios – the first relating to an imbalance in the population dynamics of language speakers in a single geographical area, and the second to do with spatial heterogeneity, where language preferences are specific to different geographical regions. For each of these, the investigation of paradigmatic situations leads us to a quantitative understanding of the conditions leading to language coexistence. We also obtain predictions of the number of surviving languages as a function of various model parameters.
Tasks
Published	2020-03-10
URL	https://arxiv.org/abs/2003.04748v1
PDF	https://arxiv.org/pdf/2003.04748v1.pdf
PWC	https://paperswithcode.com/paper/on-the-coexistence-of-competing-languages
Repo
Framework

Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization


Title	Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization
Authors	Vikas K. Garg, Adam Kalai, Katrina Ligett, Zhiwei Steven Wu
Abstract	Domain generalization is the problem of machine learning when the training data and the test data come from different data domains. We present a simple theoretical model of learning to generalize across domains in which there is a meta-distribution over data distributions, and those data distributions may even have different supports. In our model, the training data given to a learning algorithm consists of multiple datasets each from a single domain drawn in turn from the meta-distribution. We study this model in three different problem settings—a multi-domain Massart noise setting, a decision tree multi-dataset setting, and a feature selection setting, and find that computationally efficient, polynomial-sample domain generalization is possible in each. Experiments demonstrate that our feature selection algorithm indeed ignores spurious correlations and improves generalization.
Tasks	Domain Generalization, Feature Selection
Published	2020-02-13
URL	https://arxiv.org/abs/2002.05660v1
PDF	https://arxiv.org/pdf/2002.05660v1.pdf
PWC	https://paperswithcode.com/paper/learn-to-expect-the-unexpected-probably
Repo
Framework

Generalized Kernel-Based Dynamic Mode Decomposition


Title	Generalized Kernel-Based Dynamic Mode Decomposition
Authors	Patrick Heas, Cedric Herzet, Benoit Combes
Abstract	Reduced modeling in high-dimensional reproducing kernel Hilbert spaces offers the opportunity to approximate efficiently non-linear dynamics. In this work, we devise an algorithm based on low rank constraint optimization and kernel-based computation that generalizes a recent approach called “kernel-based dynamic mode decomposition”. This new algorithm is characterized by a gain in approximation accuracy, as evidenced by numerical simulations, and in computational complexity.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04375v1
PDF	https://arxiv.org/pdf/2002.04375v1.pdf
PWC	https://paperswithcode.com/paper/generalized-kernel-based-dynamic-mode
Repo
Framework

Sharp Rate of Convergence for Deep Neural Network Classifiers under the Teacher-Student Setting


Title	Sharp Rate of Convergence for Deep Neural Network Classifiers under the Teacher-Student Setting
Authors	Tianyang Hu, Zuofeng Shang, Guang Cheng
Abstract	Classifiers built with neural networks handle large-scale high dimensional data, such as facial images from computer vision, extremely well while traditional statistical methods often fail miserably. In this paper, we attempt to understand this empirical success in high dimensional classification by deriving the convergence rates of excess risk. In particular, a teacher-student framework is proposed that assumes the Bayes classifier to be expressed as ReLU neural networks. In this setup, we obtain a sharp rate of convergence, i.e., $\tilde{O}_d(n^{-2/3})$, for classifiers trained using either 0-1 loss or hinge loss. This rate can be further improved to $\tilde{O}_d(n^{-1})$ when the data distribution is separable. Here, $n$ denotes the sample size. An interesting observation is that the data dimension only contributes to the $\log(n)$ term in the above rates. This may provide one theoretical explanation for the empirical successes of deep neural networks in high dimensional classification, particularly for structured data.
Tasks
Published	2020-01-19
URL	https://arxiv.org/abs/2001.06892v2
PDF	https://arxiv.org/pdf/2001.06892v2.pdf
PWC	https://paperswithcode.com/paper/optimal-rate-of-convergence-for-deep-neural
Repo
Framework

Continual Graph Learning


Title	Continual Graph Learning
Authors	Fan Zhou, Chengtai Cao, Ting Zhong, Kunpeng Zhang, Goce Trajcevski, Ji Geng
Abstract	Graph Neural Networks (GNNs) have recently received significant research attention due to their prominent performance on a variety of graph-related learning tasks. Most of the existing works focus on either static or dynamic graph settings, addressing a particular task, e.g., node/graph classification, link prediction. In this work, we investigate the question: can GNNs be applied to continuously learning a sequence of tasks? Towards that, we explore the Continual Graph Learning (CGL) paradigm and we present the Experience Replay based framework ER-GNN for CGL to address the catastrophic forgetting problem in existing GNNs. ER-GNN stores knowledge from previous tasks as experiences and replays them when learning new tasks to mitigate the forgetting issue. We propose three experience node selection strategies: mean of features, coverage maximization and influence maximization, to guide the process of selecting experience nodes. Extensive experiments on three benchmark datasets demonstrate the effectiveness of ER-GNN and shed light on the incremental (non-Euclidean) graph structure learning.
Tasks	Graph Classification, Link Prediction
Published	2020-03-22
URL	https://arxiv.org/abs/2003.09908v1
PDF	https://arxiv.org/pdf/2003.09908v1.pdf
PWC	https://paperswithcode.com/paper/continual-graph-learning
Repo
Framework

Improving Embedding Extraction for Speaker Verification with Ladder Network


Title	Improving Embedding Extraction for Speaker Verification with Ladder Network
Authors	Fei Tao, Gokhan Tur
Abstract	Speaker verification is an established yet challenging task in speech processing and a very vibrant research area. Recent speaker verification (SV) systems rely on deep neural networks to extract high-level embeddings which are able to characterize the users’ voices. Most of the studies have investigated on improving the discriminability of the networks to extract better embeddings for performances improvement. However, only few research focus on improving the generalization. In this paper, we propose to apply the ladder network framework in the SV systems, which combines the supervised and unsupervised learning fashions. The ladder network can make the system to have better high-level embedding by balancing the trade-off to keep/discard as much useful/useless information as possible. We evaluated the framework on two state-of-the-art SV systems, d-vector and x-vector, which can be used for different use cases. The experiments showed that the proposed approach relatively improved the performance by 10% at most without adding parameters and augmented data.
Tasks	Speaker Verification
Published	2020-03-20
URL	https://arxiv.org/abs/2003.09125v1
PDF	https://arxiv.org/pdf/2003.09125v1.pdf
PWC	https://paperswithcode.com/paper/improving-embedding-extraction-for-speaker
Repo
Framework