Search Results for author:
Found 148 papers, 36 papers with code
SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds
We achieve so by introducing efficient network architecture and improving step distillation.
DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
Rehearsal-based approaches are a mainstay of continual learning (CL).
Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
We call this 'model parsing of adversarial attacks' - a task to uncover 'arcana' in terms of the concealed VM information in attacks.
DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network
To this end, a novel framework termed Mathematical Architecture Design for Deep CNN (DeepMAD) is proposed to design high-performance CNN models in a principled way.
Ranked #1 on
Neural Architecture Search
on ImageNet
Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge
With the ever-increasing popularity of edge devices, it is necessary to implement real-time segmentation on the edge for autonomous driving and many other applications.
Rethinking Vision Transformers for MobileNet Size and Speed
With the success of Vision Transformers (ViTs) in computer vision tasks, recent arts try to optimize the performance and complexity of ViTs to enable efficient deployment on mobile devices.
All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management
By re-configuring the model to the corresponding pruning ratio for a specific execution frequency (and voltage), we are able to achieve stable inference speed, i. e., keeping the difference in speed performance under various execution frequencies as small as possible.
Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors
In this paper, we uncover them by model checkpoints' gradients, forming the proposed self-ensemble protection (SEP), which is very effective because (1) learning on examples ignored during normal training tends to yield DNNs ignoring normal examples; (2) checkpoints' cross-model gradients are close to orthogonal, meaning that they are as diverse as DNNs with different architectures.
You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model
To handle this challenge, we propose a novel early exiting strategy for unified visual language models, which allows dynamically skip the layers in encoder and decoder simultaneously in term of input layer-wise similarities with multiple times of early exiting, namely \textbf{MuE}.
Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization.
HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers
While vision transformers (ViTs) have continuously achieved new milestones in the field of computer vision, their sophisticated network architectures with high computation and memory costs have impeded their deployment on resource-limited edge devices.
Data Level Lottery Ticket Hypothesis for Vision Transformers
That is, there exists a subset of input image patches such that a ViT can be trained from scratch by using only this subset of patches and achieve similar accuracy to the ViTs trained by using all image patches.
Pruning Adversarially Robust Neural Networks without Adversarial Examples
Adversarial pruning compresses models while preserving robustness.
Advancing Model Pruning via Bi-level Optimization
To reduce the computation overhead, various efficient 'one-shot' pruning methods have been developed, but these schemes are usually unable to find winning tickets as good as IMP.
Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training
Therefore, we analyze the feasibility and potentiality of using the layer freezing technique in sparse training and find it has the potential to save considerable training costs.
SparCL: Sparse Continual Learning on the Edge
SparCL achieves both training acceleration and accuracy preservation through the synergy of three aspects: weight sparsity, data efficiency, and gradient sparsity.
StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks
Obstacle detection is a safety-critical problem in robot navigation, where stereo matching is a popular vision-based approach.
PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems
In this paper, we propose a method for training quantized networks to incorporate PIM quantization, which is ubiquitous to all PIM systems.
Understanding Time Variations of DNN Inference in Autonomous Driving
Understanding the time variations of the DNN inference becomes a fundamental challenge in real-time scheduling for autonomous driving.
Survey: Exploiting Data Redundancy for Optimization of Deep Learning
It surveys hundreds of recent papers on the topic, introduces a novel taxonomy to put the various techniques into a single categorization framework, offers a comprehensive description of the main methods used for exploiting data redundancy in improving multiple kinds of DNNs on data, and points out a set of research opportunities for future to explore.
Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Instead of measuring the speed on mobile devices at each iteration during the search process, a speed model incorporated with compiler optimizations is leveraged to predict the inference latency of the SR block with various width configurations for faster convergence.
Continual Few-Shot Learning with Adversarial Class Storage
In this paper, we define a new problem called continual few-shot learning, in which tasks arrive sequentially and each task is associated with a few training samples.
Quantum Neural Network Compression
Model compression, such as pruning and quantization, has been widely applied to optimize neural networks on resource-limited classical devices.
CoCoPIE XGen: A Full-Stack AI-Oriented Optimizing Framework
There is a growing demand for shifting the delivery of AI capability from data centers on the cloud to edge or end devices, exemplified by the fast emerging real-time AI-based apps running on smartphones, AR/VR devices, autonomous vehicles, and various IoT devices.
Understanding EFL Student Idea Generation Strategies for Creative Writing with NLG Tools
This study explores strategies adopted by EFL students when searching for ideas using NLG tools, evaluating ideas generated by NLG tools and selecting NLG tools for ideas generation.
Real-Time Portrait Stylization on the Edge
In this work we demonstrate real-time portrait stylization, specifically, translating self-portrait into cartoon or anime style on mobile devices.
EfficientFormer: Vision Transformers at MobileNet Speed
Our work proves that properly designed transformers can reach extremely low latency on mobile devices while maintaining high performance.
Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization
By combining the structural reparameterization and PaS, we successfully searched out a new family of VGG-like and lightweight networks, which enable the flexibility of arbitrary width with respect to each layer instead of each stage.
Neural Network-based OFDM Receiver for Resource Constrained IoT Devices
Here, ML blocks replace the individual processing blocks of an OFDM receiver, and we specifically describe this swapping for the legacy channel estimation, symbol demapping, and decoding blocks with Neural Networks (NNs).
Deep neural network goes lighter: A case study of deep compression techniques on automatic RF modulation recognition for Beyond 5G networks
Automatic RF modulation recognition is a primary signal intelligence (SIGINT) technique that serves as a physical layer authentication enabler and automated signal processing scheme for the beyond 5G and military networks.
F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization
Our approach achieves comparable and better performance, when compared not only to existing quantization techniques with INT32 multiplication or floating-point arithmetic, but also to the full-precision counterparts, achieving state-of-the-art performance.
Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets
The lottery ticket hypothesis (LTH) has shown that dense models contain highly sparse subnetworks (i. e., winning tickets) that can be trained in isolation to match full accuracy.
AirNN: Neural Networks with Over-the-Air Convolution via Reconfigurable Intelligent Surfaces
In this paper, we design and implement the first-of-its-kind over-the-air convolution and demonstrate it for inference tasks in a convolutional neural network (CNN).
VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer
To the best of our knowledge, this is the first time quantization has been incorporated into ViT acceleration on FPGAs with the help of a fully automatic framework to guide the quantization strategy on the software side and the accelerator implementations on the hardware side given the target frame rate.
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning
Moreover, our framework can guarantee the identified model to meet resource specifications of mobile devices and FPGA, and even achieve the real-time execution of DeiT-T on mobile platforms.
Compact Multi-level Sparse Neural Networks with Input Independent Dynamic Rerouting
Deep neural networks (DNNs) have shown to provide superb performance in many real life applications, but their large computation cost and storage requirement have prevented them from being deployed to many edge and internet-of-things (IoT) devices.
Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration
Weight pruning is an effective model compression technique to tackle the challenges of achieving real-time deep neural network (DNN) inference on mobile devices.
ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA
Our proposed ILMPQ DNN quantization framework achieves 70. 73 Top1 accuracy in ResNet-18 on the ImageNet dataset.
RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions
Specifically, this is the first effort to assign mixed quantization schemes and multiple precisions within layers -- among rows of the DNN weight matrix, for simplified operations in hardware inference, while preserving accuracy.
ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
Our experimental results show that the certified accuracy is increased from 36. 3% (the state-of-the-art certified detection) to 60. 4% on the ImageNet dataset, largely pushing the certified defenses for practical use.
MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge
Systematical evaluation on accuracy, training speed, and memory footprint are conducted, where the proposed MEST framework consistently outperforms representative SOTA works.
Enabling Level-4 Autonomous Driving on a Single $1k Off-the-Shelf Card
Autonomous driving is of great interest in both research and industry.
HFSP: A Hardware-friendly Soft Pruning Framework for Vision Transformers
Recently, Vision Transformer (ViT) has continuously established new milestones in the computer vision field, while the high computation and memory cost makes its propagation in industrial production difficult.
Lottery Tickets can have Structural Sparsity
The lottery ticket hypothesis (LTH) has shown that dense models contain highly sparse subnetworks (i. e., $\textit{winning tickets}$) that can be trained in isolation to match full accuracy.
Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks
We implement ESB as an accelerator and quantitatively evaluate its efficiency on FPGAs.
DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion
Deep Neural Networks (DNNs) have emerged as the core enabler of many major applications on mobile devices.
GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity
It necessitates the sparse model inference via weight pruning, i. e., DNN weight sparsity, and it is desirable to design a new DNN weight sparsity scheme that can facilitate real-time inference on mobile devices while preserving a high sparse model accuracy.
Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search
Though recent years have witnessed remarkable progress in single image super-resolution (SISR) tasks with the prosperous development of deep neural networks (DNNs), the deep learning methods are confronted with the computation and memory consumption issues in practice, especially for resource-limited platforms such as mobile devices.
CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference
A compact, accurate, and bitwidth-programmable in-memory computing (IMC) static random-access memory (SRAM) macro, named CAP-RAM, is presented for energy-efficient convolutional neural network (CNN) inference.
Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Based on our analysis, we summarize a guideline for parameter settings in regards of specific architecture characteristics, which we hope to catalyze the research progress on the topic of lottery ticket hypothesis.
Achieving Real-Time Object Detection on MobileDevices with Neural Pruning Search
Object detection plays an important role in self-driving cars for security development.
Effective Model Sparsification by Scheduled Grow-and-Prune Methods
It addresses the shortcomings of the previous works by repeatedly growing a subset of layers to dense and then pruning them back to sparse after some training.
Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI
More importantly, our method does not require extra hardware cost compared to the traditional two-column mapping scheme.
FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
With weights stored in the ReRAM crossbar cells as conductance, when the input vector is applied to word lines, the matrix-vector multiplication results can be generated as the current in bit lines.
Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression
Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices.
Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices
The rapid development of autonomous driving, abnormal behavior detection, and behavior recognition makes an increasing demand for multi-person pose estimation-based applications, especially on mobile platforms.
A Compression-Compilation Framework for On-mobile Real-time BERT Applications
In this paper, we propose a compression-compilation co-design framework that can guarantee the identified model to meet both resource and real-time specifications of mobile devices.
Teachers Do More Than Teach: Compressing Image-to-Image Models
In this work, we aim to address these issues by introducing a teacher network that provides a search space in which efficient network architectures can be found, in addition to performing knowledge distillation.
Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?
In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) (Frankle & Carbin, 2018) pointed out that there could exist a winning ticket (i. e., a properly pruned sub-network together with original weight initialization) that can achieve competitive performance than the original dense network.
Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-Point
Model quantization has emerged as a mandatory technique for efficient inference with advanced Deep Neural Networks (DNN).
Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
3D object detection is an important task, especially in the autonomous driving application domain.
Learn-Prune-Share for Lifelong Learning
In lifelong learning, we wish to maintain and update a model (e. g., a neural network classifier) in the presence of new classification tasks that arrive sequentially.
Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework
Unlike existing methods that use the same quantization scheme for all weights, we propose the first solution that applies different quantization schemes for different rows of the weight matrix.
NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
With the increasing demand to efficiently deploy DNNs on mobile edge devices, it becomes much more important to reduce unnecessary computation and increase the execution speed.
ClickTrain: Efficient and Accurate End-to-End Deep Learning Training via Fine-Grained Architecture-Preserving Pruning
Moreover, compared with the state-of-the-art pruning-during-training approach, ClickTrain provides significant improvements both accuracy and compression ratio on the tested CNN models and datasets, under similar limited training time.
DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search
The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment.
Simultaneous Relevance and Diversity: A New Recommendation Inference Approach
Heterogeneous inference achieves divergent relevance, where relevance and diversity support each other as two collaborating objectives in one recommendation model, and where recommendation diversity is an inherent outcome of the relevance inference process.
MSP: An FPGA-Specific Mixed-Scheme, Multi-Precision Deep Neural Network Quantization Framework
To tackle the limited computing and storage resources in edge devices, model compression techniques have been widely used to trim deep neural network (DNN) models for on-device inference execution.
Real-Time Execution of Large-scale Language Models on Mobile
Our framework can guarantee the identified model to meet both resource and real-time specifications of mobile devices, thus achieving real-time execution of large transformer-based models like BERT variants.
YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design
In this work, we propose YOLObile framework, a real-time object detection on mobile devices via compression-compilation co-design.
ESMFL: Efficient and Secure Models for Federated Learning
Nowadays, Deep Neural Networks are widely applied to various domains.
AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency
Based on the neural network attention mechanism, we propose a comprehensive dynamic optimization framework including (1) testing-phase channel and column feature map pruning, as well as (2) training-phase optimization by targeted dropout.
One for Many: Transfer Learning for Building HVAC Control
Traditional HVAC control methods are typically based on creating explicit physical models for building thermal dynamics, which often require significant effort to develop and are difficult to achieve sufficient accuracy and efficiency for runtime building control and scalability for field implementations.
RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices
The vanilla sparsity removes whole kernel groups, while KGS sparsity is a more fine-grained structured sparsity that enjoys higher flexibility while exploiting full on-device parallelism.
Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization
High-end mobile platforms rapidly serve as primary computing devices for a wide range of Deep Neural Network (DNN) applications.
A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods
To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categories, i. e., static regularization-based pruning and dynamic regularization-based pruning.
CoCoPIE: Making Mobile AI Sweet As PIE --Compression-Compilation Co-Design Goes a Long Way
Assuming hardware is the major constraint for enabling real-time mobile intelligence, the industry has mainly dedicated their efforts to developing specialized hardware accelerators for machine learning and inference.
A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework
Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices.
RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition
Recurrent neural networks (RNNs) based automatic speech recognition has nowadays become prevalent on mobile devices such as smart phones.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Efficient Training of Deep Convolutional Neural Networks by Augmentation in Embedding Space
However, fine-tuning a transfer model with data augmentation in the raw input space has a high computational cost to run the full network for every augmented input.
PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators
Weight pruning is a powerful technique to realize model compression.
SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency
Structured weight pruning is a representative model compression technique of DNNs for hardware efficiency and inference accelerations.
BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method
Accelerating DNN execution on various resource-limited computing platforms has been a long-standing problem.
An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms.
Embedding Compression with Isotropic Iterative Quantization
Continuous representation of words is a standard component in deep learning-based NLP models.
PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning
Weight pruning of DNNs is proposed, but existing schemes represent two extremes in the design space: non-structured pruning is fine-grained, accurate, but not hardware friendly; structured pruning is coarse-grained, hardware-efficient, but with higher accuracy loss.
DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks
As a further optimization, we propose a density-adaptive regular-block (DARB) pruning that outperforms prior structured pruning work with high pruning ratio and decoding efficiency.
Deep Compressed Pneumonia Detection for Low-Power Embedded Devices
Deep neural networks (DNNs) have been expanded into medical fields and triggered the revolution of some medical applications by extracting complex features and achieving high accuracy and performance, etc.
Adversarial T-shirt! Evading Person Detectors in A Physical World
To the best of our knowledge, this is the first work that models the effect of deformation for designing physical adversarial examples with respect to-rigid objects such as T-shirts.
SPEC2: SPECtral SParsE CNN Accelerator on FPGAs
On the other hand, weight pruning techniques address the redundancy in model parameters by converting dense convolutional kernels into sparse ones.
REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs
To achieve real-time, highly-efficient implementations on FPGA, we present the detailed hardware implementation of block circulant matrices on CONV layers and develop an efficient processing element (PE) structure supporting the heterogeneous weight quantization, CONV dataflow and pipelining techniques, design optimization, and a template-based automatic synthesis framework to optimally exploit hardware resource.
Reweighted Proximal Pruning for Large-Scale Language Representation
Is it possible to compress these large-scale language representation models?
PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices
Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method.
An Ultra-Efficient Memristor-Based DNN Framework with Structured Weight Pruning and Quantization Using ADMM
Memristor-based weight pruning and weight quantization have been seperately investigated and proven effectiveness in reducing area and power consumption compared to the original DNN model.
Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation
To mitigate the challenges, the memristor crossbar array has emerged as an intrinsically suitable matrix computation and low-power acceleration framework for DNN applications.
Protecting Neural Networks with Hierarchical Random Switching: Towards Better Robustness-Accuracy Trade-off for Stochastic Defenses
However, one critical drawback of current defenses is that the robustness enhancement is at the cost of noticeable performance degradation on legitimate data, e. g., large drop in test accuracy.
A Stochastic-Computing based Deep Learning Framework using Adiabatic Quantum-Flux-Parametron SuperconductingTechnology
Further, the application of SC has been investigated in DNNs in prior work, and the suitability has been illustrated as SC is more compatible with approximate computations.
AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates
This work proposes AutoCompress, an automatic structured pruning framework with the following key performance improvements: (i) effectively incorporate the combination of structured pruning schemes in the automatic process; (ii) adopt the state-of-art ADMM-based structured weight pruning as the core algorithm, and propose an innovative additional purification step for further weight reduction without accuracy loss; and (iii) develop effective heuristic search method enhanced by experience-based guided search, replacing the prior deep reinforcement learning technique which has underlying incompatibility with the target pruning problem.
Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?
Based on the proposed comparison framework, with the same accuracy and quantization, the results show that non-structrued pruning is not competitive in terms of both storage and computation efficiency.
Robust Sparse Regularization: Simultaneously Optimizing Neural Network Robustness and Compactness
In this work, we show that shrinking the model size through proper weight pruning can even be helpful to improve the DNN robustness under adversarial attack.
Brain-inspired reverse adversarial examples
On contrast, current state-of-the-art deep learning approaches heavily depend on the variety of training samples and the capacity of the network.
Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks
Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability. We propose the fault sneaking attack on DNNs, where the adversary aims to misclassify certain input images into any target labels by modifying the DNN parameters.
Interpreting and Evaluating Neural Network Robustness
Recently, adversarial deception becomes one of the most considerable threats to deep neural networks.
Toward Extremely Low Bit and Lossless Accuracy in DNNs with Progressive ADMM
Weight quantization is one of the most important techniques of Deep Neural Networks (DNNs) model compression method.
26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone
With the rapid emergence of a spectrum of high-end mobile devices, many applications that required desktop-level computation capability formerly can now run on these devices without any problem.
ResNet Can Be Pruned 60x: Introducing Network Purification and Unused Path Removal (P-RM) after Weight Pruning
The state-of-art DNN structures involve high computation and great demand for memory storage which pose intensive challenge on DNN framework resources.
Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation
In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes it possible to generate images of natural scenes in arbitrary viewpoints, based on an image of the scene and a novel semantic map.
Bird View Synthesis
Cross-View Image-to-Image Translation
+1
Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds
In this paper we will use deep learning based medical image segmentation as a vehicle and demonstrate that interestingly, machine and human view the compression quality differently.
Adversarial Robustness vs Model Compression, or Both?
Furthermore, this work studies two hypotheses about weight pruning in the conventional setting and finds that weight pruning is essential for reducing the network model size in the adversarial setting, training a small model from scratch even with inherited initialization from the large model cannot achieve both adversarial robustness and high standard accuracy.
Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMM
A recent work developed a systematic frame-work of DNN weight pruning using the advanced optimization technique ADMM (Alternating Direction Methods of Multipliers), achieving one of state-of-art in weight pruning results.
CircConv: A Structured Convolution with Low Complexity
Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications.
ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers
The first part of ADMM-NN is a systematic, joint framework of DNN weight pruning and quantization using ADMM.
E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs
It is a challenging task to have real-time, efficient, and accurate hardware RNN implementations because of the high sensitivity to imprecision accumulation and the requirement of special activation function implementations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM
Both DNN weight pruning and clustering/quantization, as well as their combinations, can be solved in a unified manner.
Progressive Weight Pruning of Deep Neural Networks using ADMM
Motivated by dynamic programming, the proposed method reaches extremely high pruning rate by using partial prunings with moderate pruning rates.
Interpreting Adversarial Robustness: A View from Decision Surface in Input Space
One popular hypothesis of neural network generalization is that the flat local minima of loss surface in parameter space leads to good generalization.
Structured Adversarial Attack: Towards General Implementation and Better Interpretability
When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example.
StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs
Without loss of accuracy on the AlexNet model, we achieve 2. 58X and 3. 65X average measured speedup on two GPUs, clearly outperforming the prior work.
Adversarial Meta-Learning
Meta-learning enables a model to learn from very limited data to undertake a new task.
Towards Robust Training of Neural Networks by Regularizing Adversarial Gradients
In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications. However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws intrinsic to the network structures.
Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks using Stochastic Computing
Recently, Deep Convolutional Neural Network (DCNN) has achieved tremendous success in many machine learning applications.
Learning Topics using Semantic Locality
The topic modeling discovers the latent topic probability of the given text documents.
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
We first formulate the weight pruning problem of DNNs as a nonconvex optimization problem with combinatorial constraints specifying the sparsity requirements, and then adopt the ADMM framework for systematic weight pruning.
An ADMM-Based Universal Framework for Adversarial Attacks on Deep Neural Networks
In the literature, the added distortions are usually measured by L0, L1, L2, and L infinity norms, namely, L0, L1, L2, and L infinity attacks, respectively.
Structured Weight Matrices-Based Hardware Accelerators in Deep Neural Networks: FPGAs and ASICs
For FPGA implementations on deep convolutional neural networks (DCNNs), we achieve at least 152X and 72X improvement in performance and energy efficiency, respectively using the SWM-based framework, compared with the baseline of IBM TrueNorth processor under same accuracy constraints using the data set of MNIST, SVHN, and CIFAR-10.
C3PO: Database and Benchmark for Early-stage Malicious Activity Detection in 3D Printing
It is of vital importance to enable 3D printers to identify the objects to be printed, so that the manufacturing procedure of an illegal weapon can be terminated at the early stage.
Efficient Recurrent Neural Networks using Structured Matrices in FPGAs
Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations.
Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples
Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recently.
On the Universal Approximation Property and Equivalence of Stochastic Computing-based Neural Networks and Binary Neural Networks
Based on the universal approximation property, we further prove that SCNNs and BNNs exhibit the same energy complexity.
C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs
The previous work proposes to use a pruning based compression technique to reduce the model size and thus speedups the inference on FPGAs.
DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework
To reduce the data storage and transfer overhead in smart resource-limited Internet-of-Thing (IoT) systems, effective data compression is a "must-have" feature before transferring real-time produced dataset for training or classification.
Model-Free Control for Distributed Stream Data Processing using Deep Reinforcement Learning
Specifically, we, for the first time, propose to leverage emerging Deep Reinforcement Learning (DRL) for enabling model-free control in DSDPSs; and present design, implementation and evaluation of a novel and highly effective DRL-based control framework, which minimizes average end-to-end tuple processing time by jointly learning the system environment via collecting very limited runtime statistics data and making decisions under the guidance of powerful Deep Neural Networks.
Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia.
Systematic Weight Pruning of DNNs using Alternating Direction Method of Multipliers
We present a systematic weight pruning framework of deep neural networks (DNNs) using the alternating direction method of multipliers (ADMM).
Image Dataset for Visual Objects Classification in 3D Printing
The rapid development in additive manufacturing (AM), also known as 3D printing, has brought about potential risk and security issues along with significant benefits.
Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks
In this work, we for the first time investigate the multi-factor adversarial attack problem in practical model optimized deep learning systems by jointly considering the DNN model-reshaping (e. g. HashNet based deep compression) and the input perturbations.
An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing
However, in these works, the memory design optimization is neglected for weight storage, which will inevitably result in large hardware cost.
VIBNN: Hardware Acceleration of Bayesian Neural Networks
In this paper, we propose VIBNN, an FPGA-based hardware accelerator design for variational inference on BNNs.
Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data
This paper presents the first deep reinforcement learning (DRL) framework to estimate the optimal Dynamic Treatment Regimes from observational medical data.
Experience-driven Networking: A Deep Reinforcement Learning based Approach
Modern communication networks have become very complicated and highly dynamic, which makes them hard to model, predict and control.
FFT-Based Deep Learning Deployment in Embedded Systems
The large model size of DNNs, while providing excellent accuracy, also burdens the embedded platforms with intensive computation and storage.
A Memristor-Based Optimization Framework for AI Applications
In addition to ADMM, implementation of a customized power iteration (PI) method for eigenvalue/eigenvector computation using memristor crossbars is discussed.
Deep Reinforcement Learning: Framework, Applications, and Embedded Implementations
The recent breakthroughs of deep reinforcement learning (DRL) technique in Alpha Go and playing Atari have set a good example in handling large state and actions spaces of complicated control problems.
CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy.
A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning
Automatic decision-making approaches, such as reinforcement learning (RL), have been applied to (partially) solve the resource allocation problem adaptively in the cloud computing system.
Hardware-Driven Nonlinear Activation for Stochastic Computing Based Deep Convolutional Neural Networks
Recently, Deep Convolutional Neural Networks (DCNNs) have made unprecedented progress, achieving the accuracy close to, or even better than human-level perception in various tasks.
Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks.
SC-DCNN: Highly-Scalable Deep Convolutional Neural Network using Stochastic Computing
Stochastic Computing (SC), which uses bit-stream to represent a number within [-1, 1] by counting the number of ones in the bit-stream, has a high potential for implementing DCNNs with high scalability and ultra-low hardware footprint.
