
SEALing Neural Network Models in Secure Deep Learning Accelerators
Deep learning (DL) accelerators are increasingly deployed on edge device...
read it

Adversarial Graph Representation Adaptation for CrossDomain Facial Expression Recognition
Data inconsistency and bias are inevitable among different facial expres...
read it

Brain Tumor Anomaly Detection via Latent Regularized Adversarial Network
With the development of medical imaging technology, medical images have ...
read it

GNNAdvisor: An Efficient Runtime System for GNN Acceleration on GPUs
As the emerging trend of the graphbased deep learning, Graph Neural Net...
read it

SmartExchange: Trading Highercost Memory Storage/Access for Lowercost Computation
We present SmartExchange, an algorithmhardware codesign framework to t...
read it

NTIRE 2020 Challenge on Image Demoireing: Methods and Results
This paper reviews the Challenge on Image Demoireing that was part of th...
read it

TIMELY: Pushing Data Movements and Interfaces in PIM Accelerators Towards Local and in Time Domain
Resistiverandomaccessmemory (ReRAM) based processinginmemory (R^2PI...
read it

Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences
Neuromorphic data, recording frameless spike events, have attracted cons...
read it

Computation on Sparse Neural Networks: an Inspiration for Future Hardware
Neural network models are widely used in solving many challenging proble...
read it

Meta Segmentation Network for UltraResolution Medical Images
Despite recent progress on semantic segmentation, there still exist huge...
read it

Anomaly Detection by Latent Regularized Dual Adversarial Networks
Anomaly detection is a fundamental problem in computer vision area with ...
read it

Acoustic anomaly detection via latent regularized gaussian mixture generative adversarial networks
Acoustic anomaly detection aims at distinguishing abnormal acoustic sign...
read it

Novelty Detection via NonAdversarial Generative Network
Oneclass novelty detection is the process of determining if a query exa...
read it

Characterizing and Understanding GCNs on GPU
Graph convolutional neural networks (GCNs) have achieved stateofthear...
read it

SceneEncoder: SceneAware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor
Besides local features, global information plays an essential role in se...
read it

Memristor HardwareFriendly Reinforcement Learning
Recently, significant progress has been made in solving sophisticated pr...
read it

HyGCN: A GCN Accelerator with Hybrid Architecture
In this work, we first characterize the hybrid execution patterns of GCN...
read it

Exploring Adversarial Attack in Spiking Neural Networks with SpikeCompatible Gradient
Recently, backpropagation through time inspired learning algorithms are ...
read it

A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks
In recent years, plenty of metrics have been proposed to identify networ...
read it

Poq: Projectionbased Runtime Assertions for Debugging on a Quantum Computer
In this paper, we propose Poq, a runtime assertion scheme for debugging ...
read it

DARB: A DensityAware RegularBlock Pruning for Deep Neural Networks
The rapidly growing parameter volume of deep neural networks (DNNs) hind...
read it

Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization
Spiking neural network is an important family of models to emulate the b...
read it

Training HighPerformance and LargeScale Deep Neural Networks with Full 8bit Integers
Deep neural network (DNN) quantization converting floatingpoint (FP) da...
read it

AccD: A Compilerbased Framework for Accelerating Distancerelated Algorithms on CPUFPGA Platforms
As a promising solution to boost the performance of distancerelated alg...
read it

SemiSupervised Video Salient Object Detection Using PseudoLabels
Deep learningbased video salient object detection has recently achieved...
read it

Neural Network Model Extraction Attacks in Edge Devices by Hearing Architectural Hints
As neural networks continue their reach into nearly every aspect of soft...
read it

FPSA: A Full System Stack Solution for Reconfigurable ReRAMbased NN Accelerator Architecture
Neural Network (NN) accelerators with emerging ReRAM (resistive random a...
read it

QGAN: Quantized Generative Adversarial Networks
The intensive computation and memory requirements of generative adversar...
read it

A Secure and Persistent Memory System for Nonvolatile Memory
In the nonvolatile memory, ensuring the security and correctness of per...
read it

Facial Landmark Machines: A BackboneBranches Architecture with Progressive Representation Learning
Facial landmark localization plays a critical role in face recognition a...
read it

BiGANsST for Perceptual Image Superresolution
Image quality measurement is a critical problem for image superresoluti...
read it

Batch Normalization Sampling
Deep Neural Networks (DNNs) thrive in recent years in which Batch Normal...
read it

Dynamic Sparse Graph for Efficient Deep Learning
We propose to execute deep neural networks (DNNs) with dynamic and spars...
read it

Inmemory multiplication engine with SOTMRAM based stochastic computing
Processinginmemory (PIM) turns out to be a promising solution to break...
read it

Deep MultiView Clustering via Multiple Embedding
Exploring the information among multiple views usually leads to more pro...
read it

OffPolicy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy
When learning from a batch of logged bandit feedback, the discrepancy be...
read it

Crossbaraware neural network pruning
Crossbar architecture based devices have been widely adopted in neural n...
read it

Structurally Sparsified Backward Propagation for Faster Long ShortTerm Memory Training
Exploiting sparsity enables hardware systems to run neural networks fast...
read it

Weakly Supervised Salient Object Detection Using Image Labels
Deep learning based salient object detection has recently achieved great...
read it

L1Norm Batch Normalization for Efficient Training of Deep Neural Networks
Batch Normalization (BN) has been proven to be quite effective at accele...
read it

PIRT: A Runtime Framework to Enable EnergyEfficient RealTime Robotic Applications on Heterogeneous Architectures
Enabling full robotic workloads with diverse behaviors on mobile systems...
read it

Bridging the Gap Between Neural Networks and Neuromorphic Hardware with A Neural Network Compiler
Different from training common neural networks (NNs) for inference on ge...
read it

Effective Image Retrieval via Multilinear Multiindex Fusion
Multiindex fusion has demonstrated impressive performances in retrieval...
read it

Robust Kernelized MultiView SelfRepresentations for Clustering by Tensor MultiRank Minimization
Most recently, tensorSVD is implemented on multiview selfrepresentati...
read it

Joint Hierarchical Category Structure Learning and LargeScale Image Classification
We investigate the scalable image classification problem with a large nu...
read it

On Unifying MultiView SelfRepresentations for Clustering by Tensor MultiRank Minimization
In this paper, we address the multiview subspace clustering problem. Ou...
read it

DLAU: A Scalable Deep Learning Accelerator Unit on FPGA
As the emerging field of machine learning, deep learning shows excellent...
read it

A RealTime and EnergyEfficient Implementation of DifferenceofGaussian with Flexible ThinFilm Transistors
With many advantageous features, softness and better biocompatibility, f...
read it

Weighted Schatten pNorm Minimization for Image Denoising and Background Subtraction
Low rank matrix approximation (LRMA), which aims to recover the underlyi...
read it

A New LowRank Tensor Model for Video Completion
In this paper, we propose a new lowrank tensor model based on the circu...
read it
Yuan Xie
is this you? claim profile
leading the Scalable and Energyefficient Architecture Lab (SEAL) at UCSB