Search Results for author:
Found 50 papers, 13 papers with code
Towards Distributed Backdoor Attacks with Network Detection in Decentralized Federated Learning
In this paper, we experimentally demonstrate that, while directly applying DBA to decentralized FL, the attack success rate depends on the distribution of attackers in the network architecture.
Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
Mixture-of-Experts (MOE) has garnered significant attention for their ability to scale up neural networks while utilizing the same or even fewer active parameters.
Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design
By splitting videos into chunks and applying a super-resolution (SR) model to overfit each chunk, this scheme of SR models plus video chunks is able to replace traditional video transmission to enhance video quality and transmission efficiency.
FlameFinder: Illuminating Obscured Fire through Smoke with Attentive Deep Metric Learning
However, the dominance of center loss over the other losses leads to the model missing features sensitive to them.
Coupling Fairness and Pruning in a Single Run: a Bi-level Optimization Perspective
To address this, we define a fair pruning task where a sparse model is derived subject to fairness requirements.
Rethinking Graph Lottery Tickets: Graph Sparsity Matters
Therefore, we propose two techniques to improve GNN performance when the graph sparsity is high.
Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting
To reconcile such, we propose a novel method for high-quality and efficient video resolution upscaling tasks, which leverages the spatial-temporal information to accurately divide video into chunks, thus keeping the number of chunks as well as the model size to minimum.
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.
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.
CHEX: CHannel EXploration for CNN Model Compression
However, conventional pruning methods have limitations in that: they are restricted to pruning process only, and they require a fully pre-trained large model.
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.
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.
Ranked #4 on
Efficient ViTs
on ImageNet-1K (with DeiT-S)
Load-balanced Gather-scatter Patterns for Sparse Deep Neural Networks
Our experiments show that GS patterns consistently make better trade-offs between accuracy and computation efficiency compared to conventional structured sparse patterns.
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.
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.
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.
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.
A Topological-Framework to Improve Analysis of Machine Learning Model Performance
As both machine learning models and the datasets on which they are evaluated have grown in size and complexity, the practice of using a few summary statistics to understand model performance has become increasingly problematic.
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.
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.
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.
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.
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.
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.
PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators
Weight pruning is a powerful technique to realize model compression.
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.
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.
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.
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.
A SOT-MRAM-based Processing-In-Memory Engine for Highly Compressed DNN Implementation
Thus, the footprint and power consumption of SOT-MRAM PIM can be reduced, while increasing the overall system throughput at the meantime, making our proposed ADMM-based SOT-MRAM PIM more energy efficiency and suitable for embedded systems or IoT devices.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Person Re-Identification by Unsupervised Video Matching
Crucially, this model does not require pairwise labelled training data (i. e. unsupervised) therefore readily scalable to large scale camera networks of arbitrary camera pairs without the need for exhaustive data annotation for every camera pair.
