April 2, 2020

3349 words 16 mins read

Paper Group ANR 276

Accurate Stress Assessment based on functional Near Infrared Spectroscopy using Deep Learning Approach. Fault Diagnosis in Microelectronics Attachment via Deep Learning Analysis of 3D Laser Scans. Adversarial vs behavioural-based defensive AI with joint, continual and active learning: automated evaluation of robustness to deception, poisoning and c …

Accurate Stress Assessment based on functional Near Infrared Spectroscopy using Deep Learning Approach


Title	Accurate Stress Assessment based on functional Near Infrared Spectroscopy using Deep Learning Approach
Authors	Mahya Mirbagheri, Ata Jodeiri, Naser Hakimi, Vahid Zakeri, Seyed Kamaledin Setarehdan
Abstract	Stress is known as one of the major factors threatening human health. A large number of studies have been performed in order to either assess or relieve stress by analyzing the brain and heart-related signals. In this study, signals produced by functional Near-Infrared Spectroscopy (fNIRS) of the brain recorded from 10 healthy volunteers are employed to assess the stress induced by the Montreal Imaging Stress Task by means of a deep learning system. The proposed deep learning system consists of two main parts: First, the one-dimensional convolutional neural network is employed to build informative feature maps. Then, a stack of deep fully connected layers is used to predict the stress existence probability. Experiment results showed that the trained fNIRS model performs stress classification by achieving 88.52 -+ 0.77% accuracy. Employment of the proposed deep learning system trained on the fNIRS measurements leads to higher stress classification accuracy than the existing methods proposed in fNIRS studies in which the same experimental procedure has been employed. The proposed method suggests better stability with lower variation in prediction. Furthermore, its low computational cost opens up the possibility to be applied in real-time stress assessment.
Tasks
Published	2020-02-14
URL	https://arxiv.org/abs/2002.06282v1
PDF	https://arxiv.org/pdf/2002.06282v1.pdf
PWC	https://paperswithcode.com/paper/accurate-stress-assessment-based-on
Repo
Framework

Fault Diagnosis in Microelectronics Attachment via Deep Learning Analysis of 3D Laser Scans


Title	Fault Diagnosis in Microelectronics Attachment via Deep Learning Analysis of 3D Laser Scans
Authors	Nikolaos Dimitriou, Lampros Leontaris, Thanasis Vafeiadis, Dimosthenis Ioannidis, Tracy Wotherspoon, Gregory Tinker, Dimitrios Tzovaras
Abstract	A common source of defects in manufacturing miniature Printed Circuits Boards (PCB) is the attachment of silicon die or other wire bondable components on a Liquid Crystal Polymer (LCP) substrate. Typically, a conductive glue is dispensed prior to attachment with defects caused either by insufficient or excessive glue. The current practice in electronics industry is to examine the deposited glue by a human operator a process that is both time consuming and inefficient especially in preproduction runs where the error rate is high. In this paper we propose a system that automates fault diagnosis by accurately estimating the volume of glue deposits before and even after die attachment. To this end a modular scanning system is deployed that produces high resolution point clouds whereas the actual estimation of glue volume is performed by (R)egression-Net (RNet), a 3D Convolutional Neural Network (3DCNN). RNet outperforms other deep architectures and is able to estimate the volume either directly from the point cloud of a glue deposit or more interestingly after die attachment when only a small part of glue is visible around each die. The entire methodology is evaluated under operational conditions where the proposed system achieves accurate results without delaying the manufacturing process.
Tasks
Published	2020-02-25
URL	https://arxiv.org/abs/2002.10974v1
PDF	https://arxiv.org/pdf/2002.10974v1.pdf
PWC	https://paperswithcode.com/paper/fault-diagnosis-in-microelectronics
Repo
Framework

Adversarial vs behavioural-based defensive AI with joint, continual and active learning: automated evaluation of robustness to deception, poisoning and concept drift


Title	Adversarial vs behavioural-based defensive AI with joint, continual and active learning: automated evaluation of robustness to deception, poisoning and concept drift
Authors	Alexandre Dey, Marc Velay, Jean-Philippe Fauvelle, Sylvain Navers
Abstract	Recent advancements in Artificial Intelligence (AI) have brought new capabilities to behavioural analysis (UEBA) for cyber-security consisting in the detection of hostile action based on the unusual nature of events observed on the Information System.In our previous work (presented at C&ESAR 2018 and FIC 2019), we have associated deep neural networks auto-encoders for anomaly detection and graph-based events correlation to address major limitations in UEBA systems. This resulted in reduced false positive and false negative rates, improved alert explainability, while maintaining real-time performances and scalability. However, we did not address the natural evolution of behaviours through time, also known as concept drift. To maintain effective detection capabilities, an anomaly-based detection system must be continually trained, which opens a door to an adversary that can conduct the so-called “frog-boiling” attack by progressively distilling unnoticed attack traces inside the behavioural models until the complete attack is considered normal. In this paper, we present a solution to effectively mitigate this attack by improving the detection process and efficiently leveraging human expertise. We also present preliminary work on adversarial AI conducting deception attack, which, in term, will be used to help assess and improve the defense system. These defensive and offensive AI implement joint, continual and active learning, in a step that is necessary in assessing, validating and certifying AI-based defensive solutions.
Tasks	Active Learning, Anomaly Detection
Published	2020-01-13
URL	https://arxiv.org/abs/2001.11821v1
PDF	https://arxiv.org/pdf/2001.11821v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-vs-behavioural-based-defensive-ai
Repo
Framework

Root Cause Detection Among Anomalous Time Series Using Temporal State Alignment


Title	Root Cause Detection Among Anomalous Time Series Using Temporal State Alignment
Authors	Sayan Chakraborty, Smit Shah, Kiumars Soltani, Anna Swigart
Abstract	The recent increase in the scale and complexity of software systems has introduced new challenges to the time series monitoring and anomaly detection process. A major drawback of existing anomaly detection methods is that they lack contextual information to help stakeholders identify the cause of anomalies. This problem, known as root cause detection, is particularly challenging to undertake in today’s complex distributed software systems since the metrics under consideration generally have multiple internal and external dependencies. Significant manual analysis and strong domain expertise is required to isolate the correct cause of the problem. In this paper, we propose a method that isolates the root cause of an anomaly by analyzing the patterns in time series fluctuations. Our method considers the time series as observations from an underlying process passing through a sequence of discretized hidden states. The idea is to track the propagation of the effect when a given problem causes unaligned but homogeneous shifts of the underlying states. We evaluate our approach by finding the root cause of anomalies in Zillows clickstream data by identifying causal patterns among a set of observed fluctuations.
Tasks	Anomaly Detection, Time Series
Published	2020-01-04
URL	https://arxiv.org/abs/2001.01056v1
PDF	https://arxiv.org/pdf/2001.01056v1.pdf
PWC	https://paperswithcode.com/paper/root-cause-detection-among-anomalous-time
Repo
Framework

Bilevel Optimization for Differentially Private Optimization


Title	Bilevel Optimization for Differentially Private Optimization
Authors	Ferdinando Fioretto, Terrence WK Mak, Pascal Van Hentenryck
Abstract	This paper studies how to apply differential privacy to constrained optimization problems whose inputs are sensitive. This task raises significant challenges since random perturbations of the input data often render the constrained optimization problem infeasible or change significantly the nature of its optimal solutions. To address this difficulty, this paper proposes a bilevel optimization model that can be used as a post-processing step: It redistributes the noise introduced by a differentially private mechanism optimally while restoring feasibility and near-optimality. The paper shows that, under a natural assumption, this bilevel model can be solved efficiently for real-life large-scale nonlinear nonconvex optimization problems with sensitive customer data. The experimental results demonstrate the accuracy of the privacy-preserving mechanism and showcase significant benefits compared to standard approaches.
Tasks	bilevel optimization
Published	2020-01-26
URL	https://arxiv.org/abs/2001.09508v1
PDF	https://arxiv.org/pdf/2001.09508v1.pdf
PWC	https://paperswithcode.com/paper/bilevel-optimization-for-differentially
Repo
Framework

Give your Text Representation Models some Love: the Case for Basque


Title	Give your Text Representation Models some Love: the Case for Basque
Authors	Rodrigo Agerri, Iñaki San Vicente, Jon Ander Campos, Ander Barrena, Xabier Saralegi, Aitor Soroa, Eneko Agirre
Abstract	Word embeddings and pre-trained language models allow to build rich representations of text and have enabled improvements across most NLP tasks. Unfortunately they are very expensive to train, and many small companies and research groups tend to use models that have been pre-trained and made available by third parties, rather than building their own. This is suboptimal as, for many languages, the models have been trained on smaller (or lower quality) corpora. In addition, monolingual pre-trained models for non-English languages are not always available. At best, models for those languages are included in multilingual versions, where each language shares the quota of substrings and parameters with the rest of the languages. This is particularly true for smaller languages such as Basque. In this paper we show that a number of monolingual models (FastText word embeddings, FLAIR and BERT language models) trained with larger Basque corpora produce much better results than publicly available versions in downstream NLP tasks, including topic classification, sentiment classification, PoS tagging and NER. This work sets a new state-of-the-art in those tasks for Basque. All benchmarks and models used in this work are publicly available.
Tasks	Sentiment Analysis, Word Embeddings
Published	2020-03-31
URL	https://arxiv.org/abs/2004.00033v1
PDF	https://arxiv.org/pdf/2004.00033v1.pdf
PWC	https://paperswithcode.com/paper/give-your-text-representation-models-some
Repo
Framework

BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images


Title	BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
Authors	Thu Nguyen-Phuoc, Christian Richardt, Long Mai, Yong-Liang Yang, Niloy Mitra
Abstract	We present BlockGAN, an image generative model that learns object-aware 3D scene representations directly from unlabelled 2D images. Current work on scene representation learning either ignores scene background or treats the whole scene as one object. Meanwhile, work that considers scene compositionality treats scene objects only as image patches or 2D layers with alpha maps. Inspired by the computer graphics pipeline, we design BlockGAN to learn to first generate 3D features of background and foreground objects, then combine them into 3D features for the wholes cene, and finally render them into realistic images. This allows BlockGAN to reason over occlusion and interaction between objects’ appearance, such as shadow and lighting, and provides control over each object’s 3D pose and identity, while maintaining image realism. BlockGAN is trained end-to-end, using only unlabelled single images, without the need for 3D geometry, pose labels, object masks, or multiple views of the same scene. Our experiments show that using explicit 3D features to represent objects allows BlockGAN to learn disentangled representations both in terms of objects (foreground and background) and their properties (pose and identity).
Tasks	Representation Learning
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08988v2
PDF	https://arxiv.org/pdf/2002.08988v2.pdf
PWC	https://paperswithcode.com/paper/blockgan-learning-3d-object-aware-scene
Repo
Framework

Recognizing Families In the Wild (RFIW): The 4th Edition


Title	Recognizing Families In the Wild (RFIW): The 4th Edition
Authors	Joseph P. Robinson, Yu Yin, Zaid Khan, Ming Shao, Siyu Xia, Michael Stopa, Samson Timoner, Matthew A. Turk, Rama Chellappa, Yun Fu
Abstract	Recognizing Families In the Wild (RFIW): an annual large-scale, multi-track automatic kinship recognition evaluation that supports various visual kin-based problems on scales much higher than ever before. Organized in conjunction with the 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG) as a Challenge, RFIW provides a platform for publishing original work and the gathering of experts for a discussion of the next steps. This paper summarizes the supported tasks (i.e., kinship verification, tri-subject verification, and search & retrieval of missing children) in the evaluation protocols, which include the practical motivation, technical background, data splits, metrics, and benchmark results. Furthermore, top submissions (i.e., leader-board stats) are listed and reviewed as a high-level analysis on the state of the problem. In the end, the purpose of this paper is to describe the 2020 RFIW challenge, end-to-end, along with forecasts in promising future directions.
Tasks	Gesture Recognition
Published	2020-02-15
URL	https://arxiv.org/abs/2002.06303v2
PDF	https://arxiv.org/pdf/2002.06303v2.pdf
PWC	https://paperswithcode.com/paper/recognizing-families-in-the-wild-rfiw-the-4th
Repo
Framework

GarmentGAN: Photo-realistic Adversarial Fashion Transfer


Title	GarmentGAN: Photo-realistic Adversarial Fashion Transfer
Authors	Amir Hossein Raffiee, Michael Sollami
Abstract	The garment transfer problem comprises two tasks: learning to separate a person’s body (pose, shape, color) from their clothing (garment type, shape, style) and then generating new images of the wearer dressed in arbitrary garments. We present GarmentGAN, a new algorithm that performs image-based garment transfer through generative adversarial methods. The GarmentGAN framework allows users to virtually try-on items before purchase and generalizes to various apparel types. GarmentGAN requires as input only two images, namely, a picture of the target fashion item and an image containing the customer. The output is a synthetic image wherein the customer is wearing the target apparel. In order to make the generated image look photo-realistic, we employ the use of novel generative adversarial techniques. GarmentGAN improves on existing methods in the realism of generated imagery and solves various problems related to self-occlusions. Our proposed model incorporates additional information during training, utilizing both segmentation maps and body key-point information. We show qualitative and quantitative comparisons to several other networks to demonstrate the effectiveness of this technique.
Tasks
Published	2020-03-04
URL	https://arxiv.org/abs/2003.01894v1
PDF	https://arxiv.org/pdf/2003.01894v1.pdf
PWC	https://paperswithcode.com/paper/garmentgan-photo-realistic-adversarial
Repo
Framework


Title	EvolveGraph: Heterogeneous Multi-Agent Multi-Modal Trajectory Prediction with Evolving Interaction Graphs
Authors	Jiachen Li, Fan Yang, Masayoshi Tomizuka, Chiho Choi
Abstract	Multi-agent interacting systems are prevalent in the world, from pure physical systems to complicated social dynamic systems. In many applications, effective understanding of the environment and accurate trajectory prediction of interactive agents play a significant role in downstream tasks, such as decision and planning. In this paper, we propose a generic trajectory forecasting framework (named EvolveGraph) with explicit interaction modeling via a latent interaction graph among multiple heterogeneous, interactive agents. Considering the uncertainty and the possibility of different future behaviors, the model is designed to provide multi-modal prediction hypotheses. Since the interactions may be time-varying even with abrupt changes, and different modalities may have different interactions, we address the necessity and effectiveness of adaptively evolving the interaction graph and provide an effective solution. We also introduce a double-stage training pipeline which not only improves training efficiency and accelerates convergence, but also enhances model performance in terms of prediction error. The proposed framework is evaluated on multiple public benchmark datasets in various areas for trajectory prediction, where the agents cover on-road vehicles, pedestrians, cyclists and sports players. The experimental results illustrate that our approach achieves state-of-the-art performance in terms of prediction accuracy.
Tasks	Trajectory Prediction
Published	2020-03-31
URL	https://arxiv.org/abs/2003.13924v1
PDF	https://arxiv.org/pdf/2003.13924v1.pdf
PWC	https://paperswithcode.com/paper/evolvegraph-heterogeneous-multi-agent-multi
Repo
Framework

Towards GAN Benchmarks Which Require Generalization


Title	Towards GAN Benchmarks Which Require Generalization
Authors	Ishaan Gulrajani, Colin Raffel, Luke Metz
Abstract	For many evaluation metrics commonly used as benchmarks for unconditional image generation, trivially memorizing the training set attains a better score than models which are considered state-of-the-art; we consider this problematic. We clarify a necessary condition for an evaluation metric not to behave this way: estimating the function must require a large sample from the model. In search of such a metric, we turn to neural network divergences (NNDs), which are defined in terms of a neural network trained to distinguish between distributions. The resulting benchmarks cannot be “won” by training set memorization, while still being perceptually correlated and computable only from samples. We survey past work on using NNDs for evaluation and implement an example black-box metric based on these ideas. Through experimental validation we show that it can effectively measure diversity, sample quality, and generalization.
Tasks	Image Generation
Published	2020-01-10
URL	https://arxiv.org/abs/2001.03653v1
PDF	https://arxiv.org/pdf/2001.03653v1.pdf
PWC	https://paperswithcode.com/paper/towards-gan-benchmarks-which-require-1
Repo
Framework

ARMA Nets: Expanding Receptive Field for Dense Prediction


Title	ARMA Nets: Expanding Receptive Field for Dense Prediction
Authors	Jiahao Su, Shiqi Wang, Furong Huang
Abstract	Global information is essential for dense prediction problems, whose goal is to compute a discrete or continuous label for each pixel in the images. Traditional convolutional layers in neural networks, originally designed for image classification, are restrictive in these problems since their receptive fields are limited by the filter size. In this work, we propose autoregressive moving-average (ARMA) layer, a novel module in neural networks to allow explicit dependencies of output neurons, which significantly expands the receptive field with minimal extra parameters. We show experimentally that the effective receptive field of neural networks with ARMA layers expands as autoregressive coefficients become larger. In addition, we demonstrate that neural networks with ARMA layers substantially improve the performance of challenging pixel-level video prediction tasks as our model enlarges the effective receptive field.
Tasks	Image Classification, Video Prediction
Published	2020-02-15
URL	https://arxiv.org/abs/2002.11609v1
PDF	https://arxiv.org/pdf/2002.11609v1.pdf
PWC	https://paperswithcode.com/paper/arma-nets-expanding-receptive-field-for-dense
Repo
Framework

MPE: A Mobility Pattern Embedding Model for Predicting Next Locations


Title	MPE: A Mobility Pattern Embedding Model for Predicting Next Locations
Authors	Meng Chen, Xiaohui Yu, Yang Liu
Abstract	The wide spread use of positioning and photographing devices gives rise to a deluge of traffic trajectory data (e.g., vehicle passage records and taxi trajectory data), with each record having at least three attributes: object ID, location ID, and time-stamp. In this paper, we propose a novel mobility pattern embedding model called MPE to shed the light on people’s mobility patterns in traffic trajectory data from multiple aspects, including sequential, personal, and temporal factors. MPE has two salient features: (1) it is capable of casting various types of information (object, location and time) to an integrated low-dimensional latent space; (2) it considers the effect of ``phantom transitions’’ arising from road networks in traffic trajectory data. This embedding model opens the door to a wide range of applications such as next location prediction and visualization. Experimental results on two real-world datasets show that MPE is effective and outperforms the state-of-the-art methods significantly in a variety of tasks. \|
Tasks
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07782v1
PDF	https://arxiv.org/pdf/2003.07782v1.pdf
PWC	https://paperswithcode.com/paper/mpe-a-mobility-pattern-embedding-model-for
Repo
Framework

Spherical Image Generation from a Single Normal Field of View Image by Considering Scene Symmetry


Title	Spherical Image Generation from a Single Normal Field of View Image by Considering Scene Symmetry
Authors	Takayuki Hara, Tatsuya Harada
Abstract	Spherical images taken in all directions (360 degrees) allow representing the surroundings of the subject and the space itself, providing an immersive experience to the viewers. Generating a spherical image from a single normal-field-of-view (NFOV) image is convenient and considerably expands the usage scenarios because there is no need to use a specific panoramic camera or take images from multiple directions; however, it is still a challenging and unsolved problem. The primary challenge is controlling the high degree of freedom involved in generating a wide area that includes the all directions of the desired plausible spherical image. On the other hand, scene symmetry is a basic property of the global structure of the spherical images, such as rotation symmetry, plane symmetry and asymmetry. We propose a method to generate spherical image from a single NFOV image, and control the degree of freedom of the generated regions using scene symmetry. We incorporate scene-symmetry parameters as latent variables into conditional variational autoencoders, following which we learn the conditional probability of spherical images for NFOV images and scene symmetry. Furthermore, the probability density functions are represented using neural networks, and scene symmetry is implemented using both circular shift and flip of the hidden variables. Our experiments show that the proposed method can generate various plausible spherical images, controlled from symmetric to asymmetric.
Tasks	Image Generation
Published	2020-01-09
URL	https://arxiv.org/abs/2001.02993v1
PDF	https://arxiv.org/pdf/2001.02993v1.pdf
PWC	https://paperswithcode.com/paper/spherical-image-generation-from-a-single
Repo
Framework

OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems


Title	OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems
Authors	Changhee Won, Hochang Seok, Zhaopeng Cui, Marc Pollefeys, Jongwoo Lim
Abstract	In this paper, we present an omnidirectional localization and dense mapping system for a wide-baseline multiview stereo setup with ultra-wide field-of-view (FOV) fisheye cameras, which has a 360 degrees coverage of stereo observations of the environment. For more practical and accurate reconstruction, we first introduce improved and light-weighted deep neural networks for the omnidirectional depth estimation, which are faster and more accurate than the existing networks. Second, we integrate our omnidirectional depth estimates into the visual odometry (VO) and add a loop closing module for global consistency. Using the estimated depth map, we reproject keypoints onto each other view, which leads to a better and more efficient feature matching process. Finally, we fuse the omnidirectional depth maps and the estimated rig poses into the truncated signed distance function (TSDF) volume to acquire a 3D map. We evaluate our method on synthetic datasets with ground-truth and real-world sequences of challenging environments, and the extensive experiments show that the proposed system generates excellent reconstruction results in both synthetic and real-world environments.
Tasks	Depth Estimation, Visual Odometry
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08056v1
PDF	https://arxiv.org/pdf/2003.08056v1.pdf
PWC	https://paperswithcode.com/paper/omnislam-omnidirectional-localization-and
Repo
Framework