On data lake architectures and metadata management

So-called big data generally come from transactionalsystems, and even more so from the Internet of Things and social media . A data lake is a large, raw data repository that stores and manages all company databearing any format . The data lake concept remains ambiguous or fuzzy for many researchers and practitioners, who often confuse it with the Hadoop technology .…

Learning Quadruped Locomotion Policies with Reward Machines

Legged robots have been shown to be effective in navigating unstructured environments . There has been much success in learning locomotionpolicies for quadruped robots, but there is little research on how to incorporatehuman knowledge to facilitate this learning process . In this paper, wedemonstrate that human knowledge in the form of LTL formulas can be applied to quadruped locomotion learning within a Reward Machine framework .…

How to Trust Strangers Composition of Byzantine Quorum Systems

Trust is the basis of any distributed, fault-tolerant, or secure system . In systems subject to Byzantine faults, the trust assumption is usually specified through sets of processes that may fail together . Reaching consensus with asymmetric trust in the model of personal Byzantinequorum systems was shown to be impossible, if the trust assumptions of the processes diverge from each other .…

Resource Efficient Mountainous Skyline Extraction using Shallow Learning

Skyline plays a pivotal role in mountainous visual geo-localization and localization/navigation of planetary rovers/UAVs and virtual/augmented realityapplications . We present a novel mountainous skyline detection approach wherewe adapt a shallow learning approach to learn a set of filters to discriminate between edges belonging to sky-mountain boundary and others coming from different regions .…

The Diagonal Distance of CWS Codes

Quantum degeneracy in error correction is a feature unique to quantum errorcorrecting codes unlike their classically counterpart . It allows a quantumerror correcting code to correct errors even in cases when they can not pin point the error . Diagonal distance of a quantum code is animportant parameter that characterizes if it is degenerate ornot .…

MCDAL Maximum Classifier Discrepancy for Active Learning

Recent state-of-the-art active learning methods have mostly leveragedGenerative Adversarial Networks (GAN) for sample acquisition . However, GAN isusually known to suffer from instability and sensitivity to hyper-parameters . In contrast to these methods, we propose in this paper a novel active learningframework that we call Maximum Classifier Discrepancy for Active Learning(MCDAL) which takes the prediction discrepancies between multiple classifiers .…

Dynamic Proximal Unrolling Network for Compressive Sensing Imaging

CompressiveSensing Imaging (CSI) is a challenging problem and has many practical applications . Deep neural networks have been applied to this problem with promising results . But existing neural network approaches require separate models for each imaging parameter like sampling ratios, leading totraining difficulties and overfitting to specific settings .…

Entropy Derivation Operators and Huffman Trees

We build a theory of binary trees on finite multisets that categorifies, oroperationalizes, the entropy of a finite probability distribution . Multisetsoperationalize probabilities as the event outcomes of an experiment . Huffmantrees operationalize the entertainment of the distribution of these events .…

Pruning Ternary Quantization

The method significantly compressesneural network weights to a sparse ternary of [-1,0,1 . It can compress aResNet-18 model from 46 MB to 955KB and a ResNet-50 model from 99 MB to 3.3MB (~30x) The top-1 accuracy on ImageNet drops slightly from 69.7% to65.3% and from 76.15% to 74.47% .…

Standardized Max Logits A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban Scene Segmentation

Identifying unexpected objects on roads in semantic segmentation is crucial in safety-critical applications . Existing approaches use images of unexpected objects from external datasets or require additional training . We propose a simple yet effective approach that standardizes the max logits in order to align the different distributions and reflect the relative meanings of each predicted class .…

Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds

Semantic segmentation on 3D point clouds is an important task for 3D sceneunderstanding . We train a semantic point cloud segmentation network with only asmall portion of points being labeled . We argue that we can better utilize thelimited supervision information as we densely propagate the supervision signalfrom the labeled points to other points within and across the input samples .…

MCDAL Maximum Classifier Discrepancy for Active Learning

Recent state-of-the-art active learning methods have mostly leveragedGenerative Adversarial Networks (GAN) for sample acquisition . However, GAN isusually known to suffer from instability and sensitivity to hyper-parameters . In contrast to these methods, we propose in this paper a novel active learningframework that we call Maximum Classifier Discrepancy for Active Learning(MCDAL) which takes the prediction discrepancies between multiple classifiers .…

Bias Loss for Mobile Neural Networks

Compact convolutional neural networks (CNNs) have witnessed exceptionalimprovements in performance in recent years . However, they still fail toprovide the same predictive power as CNNs with a large number of parameters . Diverse features present in activation maps indicate presence of unique descriptors necessary to distinguish between objects of differentclasses .…

Making Reads in BFT State Machine Replication Fast Linearizable and Live

Practical Byzantine Fault Tolerance (PBFT) is a seminal state machinereplication protocol that achieves a performance comparable to non-replicated systems in realistic environments . One of these optimizations is read-only requests, a particular type of client request which avoids running the three-step agreement protocol and allows replicas to respond directly, thus reducing the latency of reads from five to two communication steps .…

Human Pose Estimation from Sparse Inertial Measurements through Recurrent Graph Convolution

The AAGC-LSTM combines spatial and temporal dependency in a single network operation . This is made possible by equipping graph convolutions with adjacency adaptivity, which allows for learning unknown dependencies of the human body joints . Tofurther boost accuracy, we propose longitudinal loss weighting to considernatural movement patterns, as well as body-aware contralateral dataaugmentation .…

When a crisis strikes Emotion analysis and detection during COVID 19

Understanding emotions that people express during large-scale crises helps inform policy makers and first responders about theemotional states of the population . We present CovidEmo, ~1K tweets labeled withemotions. We examine how well large pre-trained language models generalizeacross domains and crises in the task of perceived emotion prediction .…

Provident Vehicle Detection at Night for Advanced Driver Assistance Systems

Current algorithms share one limitation: They rely on directly visible objects . This is a major drawback compared to human behavior, where indirect visual cues caused by the actual object (e.g.,shadows) are already used intuitively to retrieve information . Humans already process light artifacts caused by oncoming vehicles to assume their future appearance, whereas current objectdetection systems rely on the oncoming vehicle’s direct visibility .…

ArchaeoDAL A Data Lake for Archaeological Data Management and Analytics

Archaeological data have many different formats (images,texts, sensor data) and can be structured, semi-structured and unstructured . Such variety makes data difficult to collect, store, manage, search and analyze . We propose a generic, flexible andcomplete data lake architecture . Our metadata management system exploitsgoldMEDAL, which is the most complete metadata model currently available .…

A simple yet consistent constitutive law and mortar based layer coupling schemes for thermomechanical part scale simulations of metal additive manufacturing processes

This article proposes a coupled thermomechanical finite element modeltailored to the part-scale simulation of metal additive manufacturing process . A first focus lies on the derivation of aconsistent constitutive law on basis of a Voigt-type spatial homogenizationprocedure across the relevant phases, powder, melt and solid .…

Exploring Deep Registration Latent Spaces

Explainability of deep neural networks is one of the most challenging and interesting problems in the field . We show that such an approach can decompose the highly convoluted latent latent spaces of registration pipelines in an orthogonal space with several interesting properties .…

Constellation Learning relational abstractions over objects for compositional imagination

Constellation is anetwork that learns relational abstractions of static visual scenes, and generalises these abstractions over sensory particularities . We further show that thisbasis, along with language association, provides a means to imagine sensorycontent in new ways . This work is a first step in the explicit representation of visual relationships and using them for complex cognitive procedures .…

Bias Loss for Mobile Neural Networks

Compact convolutional neural networks (CNNs) have witnessed exceptionalimprovements in performance in recent years . However, they still fail toprovide the same predictive power as CNNs with a large number of parameters . Diverse features present in activation maps indicate presence of unique descriptors necessary to distinguish between objects of differentclasses .…

Photon Starved Scene Inference using Single Photon Cameras

Single-photon cameras (SPCs) are an emergingsensing modality that are capable of capturing images with high sensitivity . Despite having minimal read-noise, images captured by SPCs in photon-starved conditions still suffer from strong shot noise . We propose photon scale-space a collection of high-SNR imagesspanning a wide range of photons-per-pixel (PPP) levels as guides to train inference model on low photon flux images .…

OLR 2021 Challenge Datasets Rules and Baselines

This paper introduces the sixth Oriental Language Recognition (OLR) 2021Challenge . It intends to improve the performance of language recognitionsystems and speech recognition systems within multilingual scenarios . The dataprofile, four tasks, two baselines, and the evaluation principles are presented .…

Score Based Point Cloud Denoising

Point clouds acquired from scanning devices are often perturbed by noise, which affects downstream tasks such as surface reconstruction and analysis . To denoise a noisy point cloud, we propose to increase the log-likelihood of each point from $p *n$ via gradient ascent .…

Unsupervised Domain Adaptive 3D Detection with Multi Level Consistency

Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets . However, drasticperformance degradation remains a critical challenge for cross-domain deployment . We propose anovel and unified framework, Multi-Level Consistency Network (MLC-Net), whichemploys a teacher-student paradigm to generate adaptive and reliablepseudo-targets .…

Finite Bit Quantization For Distributed Algorithms With Linear Convergence

This paper studies distributed algorithms for (strongly convex) compositeoptimization problems over mesh networks . Instead of focusing on a specific algorithmic design, we propose a black-boxmodel casting distributed algorithms in the form of fixed-point iterates,converging at linear rate . The algorithmic model is coupled with a novel(random) Biased Compression (BC-)rule on the quantizer design, which preserves linear convergence .…

Reservoir Computing Approach for Gray Images Segmentation

The paper proposes a novel approach for gray scale images segmentation . It is based on multiple features extraction from single feature per image pixel, using Echo state network . The newly extractedfeatures — reservoir equilibrium states — reveal hidden image characteristicsthat improve its segmentation via a clustering algorithm .…

Knowledge Rocks Adding Knowledge Assistance to Visualization Systems

Knowledge Rocks is an implementation strategy and guideline for augmenting visualization systems to knowledge-assisted visualization systems . Its centerpiece is an ontology that is able to automatically analyze andclassify input data, linked to a database to store classified instances . We provide adetailed case study by augmenting an it-security system with knowledge-assistance facilities.…

Class Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation

Surgical reports aimed at understanding inrobot-assisted surgery can contribute to documenting entry tasks and post-operative analysis . Despite the impressive outcome, the deep learningmodel degrades the performance when applied to different domains encountering domain shifts . In this work, we proposeclass-incremental domain adaptation (CIDA) with a multi-layer transformer-basedmodel to tackle the new classes and domain shift in the target domain to generate surgical reports .…

Finite Element Formulations for Beam to Solid Interaction From Embedded Fibers Towards Contact

Contact and related phenomena, such as friction, wear or elastohydrodynamiclubrication, remain as one of the most challenging problem classes in nonlinearsolid and structural mechanics . The inherentnon-smoothness of contact conditions, the design of robust discretization approaches and the implementation of efficient solution schemes seem toprovide a never ending source of hard nuts to crack .…