Search Results for author:
Found 32 papers, 4 papers with code
FedCAP: Robust Federated Learning via Customized Aggregation and Personalization
The core of FedCAP is a model update calibration mechanism to help a server capture the differences in the direction and magnitude of model updates among clients.
Online Learning via Memory: Retrieval-Augmented Detector Adaptation
This paper presents a novel way of online adapting any off-the-shelf object detection model to a novel domain without retraining the detector model.
LLM-dCache: Improving Tool-Augmented LLMs with GPT-Driven Localized Data Caching
As Large Language Models (LLMs) broaden their capabilities to manage thousands of API calls, they are confronted with complex data operations across vast datasets with significant overhead to the underlying system.
Infinite-Dimensional Feature Interaction
The past neural network design has largely focused on feature representation space dimension and its capacity scaling (e. g., width, depth), but overlooked the feature interaction space scaling.
QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation
Machine learning is evolving towards high-order models that necessitate pre-training on extensive datasets, a process associated with significant overheads.
Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble
Our experimental results demonstrate the superior performance of the MC Ensemble strategy in OOD detection compared to both the naive Deep Ensemble method and a standalone model of comparable size.
QuadraNet: Improving High-Order Neural Interaction Efficiency with Hardware-Aware Quadratic Neural Networks
Recent progress in computer vision-oriented neural network designs is mostly driven by capturing high-order neural interactions among inputs and features.
Hardware Aware Neural Architecture Search
Neural Architecture Search
Stable Diffusion For Aerial Object Detection
Aerial object detection is a challenging task, in which one major obstacle lies in the limitations of large-scale data collection and the long-tail distribution of certain classes.
QuadraLib: A Performant Quadratic Neural Network Library for Architecture Optimization and Design Exploration
The significant success of Deep Neural Networks (DNNs) is highly promoted by the multiple sophisticated DNN libraries.
Fed2: Feature-Aligned Federated Learning
Federated learning learns from scattered data by fusing collaborative models from local nodes.
A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities
With both scaling trends, new problems and challenges emerge in DL inference serving systems, which gradually trends towards Large-scale Deep learning Serving systems (LDS).
Supporting Massive DLRM Inference Through Software Defined Memory
Deep Learning Recommendation Models (DLRM) are widespread, account for a considerable data center footprint, and grow by more than 1. 5x per year.
Third ArchEdge Workshop: Exploring the Design Space of Efficient Deep Neural Networks
This paper gives an overview of our ongoing work on the design space exploration of efficient deep neural networks (DNNs).
Heterogeneous Federated Learning
Specifically, we design a feature-oriented regulation method ({$\Psi$-Net}) to ensure explicit feature information allocation in different neural network structures.
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.
Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning
In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the domain content distribution gap that is shown to be important for object detectors.
LanCe: A Comprehensive and Lightweight CNN Defense Methodology against Physical Adversarial Attacks on Embedded Multimedia Applications
Based on the detection result, we further propose a data recovery methodology to defend the physical adversarial attacks.
Gradient-free Neural Network Training by Multi-convex Alternating Optimization
To overcome these drawbacks, alternating minimization-based methods for deep neural network optimization have attracted fast-increasing attention recently.
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.
ADMM for Efficient Deep Learning with Global Convergence
However, as an emerging domain, several challenges remain, including 1) The lack of global convergence guarantees, 2) Slow convergence towards solutions, and 3) Cubic time complexity with regard to feature dimensions.
DoPa: A Comprehensive CNN Detection Methodology against Physical Adversarial Attacks
To address this issue, we propose DoPa -- a comprehensive CNN detection methodology for various physical adversarial attacks.
Interpreting and Evaluating Neural Network Robustness
Recently, adversarial deception becomes one of the most considerable threats to deep neural networks.
INTERPRETABLE CONVOLUTIONAL FILTER PRUNING
As significant redundancies inevitably present in such a structure, many works have been proposed to prune the convolutional filters for computation cost reduction.
Demystifying Neural Network Filter Pruning
We find that the filter magnitude based method fails to eliminate the filters with repetitive functionality.
Distilling Critical Paths in Convolutional Neural Networks
Neural network compression and acceleration are widely demanded currently due to the resource constraints on most deployment targets.
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.
Functionality-Oriented Convolutional Filter Pruning
As significant redundancies inevitably present in such a structure, many works have been proposed to prune the convolutional filters for computation cost reduction.
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.
HASP: A High-Performance Adaptive Mobile Security Enhancement Against Malicious Speech Recognition
In this work, we propose HASP -- a high-performance security enhancement approach to solve this security issue on mobile devices.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
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.
How convolutional neural network see the world - A survey of convolutional neural network visualization methods
Nowadays, the Convolutional Neural Networks (CNNs) have achieved impressive performance on many computer vision related tasks, such as object detection, image recognition, image retrieval, etc.
ASP:A Fast Adversarial Attack Example Generation Framework based on Adversarial Saliency Prediction
By comparing the analyzed saliency map and the adversarial perturbation distribution, we proposed a new evaluation scheme to comprehensively assess the adversarial attack precision and efficiency.
