
Robust subsamplingbased sparse Bayesian inference to tackle four challenges (large noise, outliers, data integration, and extrapolation) in the discovery of physical laws from
The derivation of physical laws is a dominant topic in scientific resear...
read it

Unrestricted Adversarial Attacks for Semantic Segmentation
Semantic segmentation is one of the most impactful applications of machi...
read it

PENet: Object Detection using Points Estimation in Aerial Images
Aerial imagery has been increasingly adopted in missioncritical tasks, ...
read it

Horseshoe Regularization for Machine Learning in Complex and Deep Models
Since the advent of the horseshoe priors for regularization, globalloca...
read it

Zooming SlowMo: Fast and Accurate OneStage SpaceTime Video SuperResolution
In this paper, we explore the spacetime video superresolution task, wh...
read it

TREND: Transferability based Robust ENsemble Design
Deep Learning models hold stateoftheart performance in many fields, b...
read it

Multilevel hypothesis testing for populations of heterogeneous networks
In this work, we consider hypothesis testing and anomaly detection on da...
read it

Fast Deep Learning for Automatic Modulation Classification
In this work, we investigate the feasibility and effectiveness of employ...
read it

City2City: Translating Place Representations across Cities
Large mobility datasets collected from various sources have allowed us t...
read it

A TwoStage Approach to FewShot Learning for Image Recognition
This paper proposes a multilayer neural network structure for fewshot ...
read it

Bayesian Sparse learning with preconditioned stochastic gradient MCMC and its applications
In this work, we propose a Bayesian type sparse deep learning algorithm....
read it

A Comparative Evaluation of SGM Variants (including a New Variant, tMGM) for Dense Stereo Matching
Our goal here is threefold: [1] To present a new densestereo matching a...
read it

LowPower Computer Vision: Status, Challenges, Opportunities
Computer vision has achieved impressive progress in recent years. Meanwh...
read it

CheckSoft : A Scalable EventDriven Software Architecture for Keeping Track of People and Things in PeopleCentric Spaces
We present CheckSoft, a scalable eventdriven software architecture for ...
read it

AdaWISH: Faster Discrete Integration via Adaptive Quantiles
Discrete integration in a high dimensional space of n variables poses fu...
read it

Safetyguaranteed Reinforcement Learning based on Multiclass Support Vector Machine
Several works have addressed the problem of incorporating constraints in...
read it

A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networks
In this era of machine learning models, their functionality is being thr...
read it

PeriNetPro: The neural processes with quantified uncertainty for crack patterns
This paper uses the peridynamic theory, which is wellsuited to crack st...
read it

Deepfakes Detection with Automatic Face Weighting
Altered and manipulated multimedia is increasingly present and widely di...
read it

TiMDNN: Ternary inMemory accelerator for Deep Neural Networks
The use of lower precision has emerged as a popular technique to optimiz...
read it

Classspecific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images
Detecting objects in a twodimensional setting is often insufficient in ...
read it

Structured Compression and Sharing of Representational Space for Continual Learning
Humans are skilled at learning adaptively and efficiently throughout the...
read it

Multilevel Training and Bayesian Optimization for Economical Hyperparameter Optimization
Hyperparameters play a critical role in the performances of many machine...
read it

Efficient Hybrid Network Architectures for Extremely Quantized Neural Networks Enabling Intelligence at the Edge
The recent advent of `Internet of Things' (IOT) has increased the demand...
read it

Deep Learning Guided Building Reconstruction from Satellite Imageryderived Point Clouds
3D urban reconstruction of buildings from remotely sensed imagery has dr...
read it

Deep Transfer Learning For Plant Center Localization
Plant phenotyping focuses on the measurement of plant characteristics th...
read it

Selfsupervised learning for fast and scalable time series hyperparameter tuning
Hyperparameters of time series models play an important role in time se...
read it

Megapixel PhotonCounting Color Imaging using Quanta Image Sensor
Quanta Image Sensor (QIS) is a singlephoton detector designed for extre...
read it

Robust datadriven discovery of governing physical laws using a new subsamplingbased sparse Bayesian method to tackle four challenges (large noise, outliers, data integration,
The derivation of physical laws is a dominant topic in scientific resear...
read it

Relevantfeatures based Auxiliary Cells for Energy Efficient Detection of Natural Errors
Deep neural networks have demonstrated stateoftheart performance on m...
read it

Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation
Spiking Neural Networks (SNNs) operate with asynchronous discrete events...
read it

Ensemble Wrapper Subsampling for Deep Modulation Classification
Subsampling of received wireless signals is important for relaxing hardw...
read it

SaliencyAware ClassAgnostic Food Image Segmentation
Advances in imagebased dietary assessment methods have allowed nutritio...
read it

Interactive Learning for Identifying Relevant Tweets to Support Realtime Situational Awareness
Various domain users are increasingly leveraging realtime social media ...
read it

Geometric AllWay Boolean Tensor Decomposition
Boolean tensor has been broadly utilized in representing high dimensiona...
read it

Automatic Foreground Extraction using MultiAgent Consensus Equilibrium
While foreground extraction is fundamental to virtual reality systems an...
read it

MEBF: a fast and efficient Boolean matrix factorization method
Boolean matrix has been used to represent digital information in many fi...
read it

A Sparse Deep Factorization Machine for Efficient CTR prediction
Clickthrough rate (CTR) prediction is a crucial task in online display ...
read it

Object classification from randomized EEG trials
New results suggest strong limits to the feasibility of classifying huma...
read it

Lowrank Tensor Bandits
In recent years, multidimensional online decision making has been playi...
read it

A New Stereo Benchmarking Dataset for Satellite Images
In order to facilitate further research in stereo reconstruction with mu...
read it

Flexible Mixture Modeling on Constrained Spaces
This paper addresses challenges in flexibly modeling multimodal data tha...
read it

Flappy Hummingbird: An Open Source Dynamic Simulation of Flapping Wing Robots and Animals
Insects and hummingbirds exhibit extraordinary flight capabilities and c...
read it

Efficient Gaussian Process Bandits by Believing only Informative Actions
Bayesian optimization is a framework for global search via maximum a pos...
read it

A Parallel Sparse Tensor Benchmark Suite on CPUs and GPUs
Tensor computations present significant performance challenges that impa...
read it

Towards Understanding the Effect of Leak in Spiking Neural Networks
Spiking Neural Networks (SNNs) are being explored to emulate the astound...
read it

3D Object Classification via Spherical Projections
In this paper, we introduce a new method for classifying 3D objects. Our...
read it

Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing
Deep convolutional neural network (DCNN) based supervised learning is a ...
read it

On Deterministic Sampling Patterns for Robust LowRank Matrix Completion
In this letter, we study the deterministic sampling patterns for the com...
read it

Deep Neural Network Architectures for Modulation Classification
In this work, we investigate the value of employing deep learning for th...
read it
Purdue University
Purdue University is a public research university in West Lafayette, Indiana, and the flagship campus of the Purdue University system.