Search Results for author:
Found 100 papers, 29 papers with code
An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design
The fast development of object detection techniques has attracted attention to developing efficient Deep Neural Networks (DNNs).
TopoNAS: Boosting Search Efficiency of Gradient-based NAS via Topological Simplification
Improving search efficiency serves as one of the crucial objectives of Neural Architecture Search (NAS).
Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling
Concretely, the proposed decoupling manner includes two ways, i. e., channel-wise decoupling and spatial-level neuron-relevant semantic consistency.
Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Images
In this paper, we propose Continual Panoptic Perception (CPP), a unified continual learning model that leverages multi-task joint learning covering pixel-level classification, instance-level segmentation and image-level perception for universal interpretation in remote sensing images.
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
Diffusion-based image generation models have achieved great success in recent years by showing the capability of synthesizing high-quality content.
DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays
Classic reinforcement learning (RL) frequently confronts challenges in tasks involving delays, which cause a mismatch between received observations and subsequent actions, thereby deviating from the Markov assumption.
QComp: A QSAR-Based Data Completion Framework for Drug Discovery
In drug discovery, in vitro and in vivo experiments reveal biochemical activities related to the efficacy and toxicity of compounds.
Panoptic Perception: A Novel Task and Fine-grained Dataset for Universal Remote Sensing Image Interpretation
Experimental results on FineGrip demonstrate the feasibility of the panoptic perception task and the beneficial effect of multi-task joint optimization on individual tasks.
AesopAgent: Agent-driven Evolutionary System on Story-to-Video Production
In the Horizontal Layer, we introduce a novel RAG-based evolutionary system that optimizes the whole video generation workflow and the steps within the workflow.
DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models
In this paper, for the first time, we systematically explore the detectability of the poisoned noise input for the backdoored diffusion models, an important performance metric yet little explored in the existing works.
When Large Language Models Meet Vector Databases: A Survey
This survey explores the synergistic potential of Large Language Models (LLMs) and Vector Databases (VecDBs), a burgeoning but rapidly evolving research area.
ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks
Low-rank compression, a popular model compression technique that produces compact convolutional neural networks (CNNs) with low rankness, has been well-studied in the literature.
In-Sensor Radio Frequency Computing for Energy-Efficient Intelligent Radar
Radio Frequency Neural Networks (RFNNs) have demonstrated advantages in realizing intelligent applications across various domains.
PETDet: Proposal Enhancement for Two-Stage Fine-Grained Object Detection
Fine-grained object detection (FGOD) extends object detection with the capability of fine-grained recognition.
Corner-to-Center Long-range Context Model for Efficient Learned Image Compression
To tackle this issue, we conduct an in-depth analysis of the performance degradation observed in existing parallel context models, focusing on two aspects: the Quantity and Quality of information utilized for context prediction and decoding.
Replay-enhanced Continual Reinforcement Learning
On the other hand, offline learning on replayed tasks while learning a new task may induce a distributional shift between the dataset and the learned policy on old tasks, resulting in forgetting.
A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application
In this paper, we present a review of CSS, committing to building a comprehensive survey on problem formulations, primary challenges, universal datasets, neoteric theories and multifarious applications.
Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory
In this paper, we propose to address CISS without exemplar memory and resolve catastrophic forgetting as well as semantic drift synchronously.
Class-Incremental Semantic Segmentation
Contrastive Learning
+2
Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation
The most recent methods of this kind measure the uncertainty of each pre-divided region for manual labelling but they suffer from redundant information and require additional efforts for region division.
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework
In our experiments, we conduct a robustness evaluation of RoBERTa models to demonstrate the effectiveness of our evaluation framework, and further show the rationality of each component in the framework.
COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models
Attention-based vision models, such as Vision Transformer (ViT) and its variants, have shown promising performance in various computer vision tasks.
Guided Focal Stack Refinement Network for Light Field Salient Object Detection
To this end, we propose a guided refinement and fusion module (GRFM) to refine focal stacks and aggregate multi-modal features.
DynamicKD: An Effective Knowledge Distillation via Dynamic Entropy Correction-Based Distillation for Gap Optimizing
This paper proposes a novel knowledge distillation algorithm based on dynamic entropy correction to reduce the gap by adjusting the student instead of the teacher.
Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing
However, it suffers from issues in terms of communication, resource of MTs, and privacy.
Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy
To defend the inference attacks and mitigate the sensitive information leakages in Federated Learning (FL), client-level Differentially Private FL (DPFL) is the de-facto standard for privacy protection by clipping local updates and adding random noise.
Improved dimension dependence of a proximal algorithm for sampling
For instance, for strongly log-concave distributions, our method has complexity bound $\tilde\mathcal{O}(\kappa d^{1/2})$ without warm start, better than the minimax bound for MALA.
Improving the Model Consistency of Decentralized Federated Learning
To mitigate the privacy leakages and communication burdens of Federated Learning (FL), decentralized FL (DFL) discards the central server and each client only communicates with its neighbors in a decentralized communication network.
SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning
Offline safe RL is of great practical relevance for deploying agents in real-world applications.
HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks
By interpreting automatic rank selection from an architecture search perspective, we develop an end-to-end solution to determine the suitable layer-wise ranks in a differentiable and hardware-aware way.
Beyond the exome: what's next in diagnostic testing for Mendelian conditions
Despite advances in clinical genetic testing, including the introduction of exome sequencing (ES), more than 50% of individuals with a suspected Mendelian condition lack a precise molecular diagnosis.
GOHSP: A Unified Framework of Graph and Optimization-based Heterogeneous Structured Pruning for Vision Transformer
We first develop a graph-based ranking for measuring the importance of attention heads, and the extracted importance information is further integrated to an optimization-based procedure to impose the heterogeneous structured sparsity patterns on the ViT models.
GUAP: Graph Universal Attack Through Adversarial Patching
Graph neural networks (GNNs) are a class of effective deep learning models for node classification tasks; yet their predictive capability may be severely compromised under adversarially designed unnoticeable perturbations to the graph structure and/or node data.
RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts
The field of text-to-image generation has made remarkable strides in creating high-fidelity and photorealistic images.
Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning
Hence, we propose Pre-trained Image Encoder for Generalizable visual reinforcement learning (PIE-G), a simple yet effective framework that can generalize to the unseen visual scenarios in a zero-shot manner.
Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks
Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there is still a lack of high-quality evaluation of those algorithms that adheres to safety constraints at each decision step under complex and unknown dynamics.
Algorithm and Hardware Co-Design of Energy-Efficient LSTM Networks for Video Recognition with Hierarchical Tucker Tensor Decomposition
Meanwhile, compared with the state-of-the-art tensor decomposed model-oriented hardware TIE, our proposed FDHT-LSTM architecture achieves better performance in throughput, area efficiency and energy efficiency, respectively on LSTM-Youtube workload.
CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustness
Considering the co-importance of model compactness and robustness in practical applications, several prior works have explored to improve the adversarial robustness of the sparse neural networks.
RoChBert: Towards Robust BERT Fine-tuning for Chinese
Despite of the superb performance on a wide range of tasks, pre-trained language models (e. g., BERT) have been proved vulnerable to adversarial texts.
Syntax-guided Localized Self-attention by Constituency Syntactic Distance
Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data.
Text Editing as Imitation Game
Text editing, such as grammatical error correction, arises naturally from imperfect textual data.
A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning
Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains.
On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation
Compared with the photometric consistency loss as well as the rigid point cloud alignment loss, the proposed DFA and VDA losses are more robust owing to the strong representation power of deep features as well as the high tolerance of voxel density to the aforementioned challenges.
Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization
A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information.
Robot Motion Planning as Video Prediction: A Spatio-Temporal Neural Network-based Motion Planner
Despite the current development in this direction, the efficient capture and processing of important sequential and spatial information, in a direct and simultaneous way, is still relatively under-explored.
RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN
Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models.
The least-used key selection method for information retrieval in large-scale Cloud-based service repositories
The experimental results show that the proposed least-used key selection method improves the service retrieval efficiency significantly compared with the designated key selection method in the case of the unequal appearing probability of parameters in service retrieval requests under three indexing models.
SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving
Safe reinforcement learning (RL) has achieved significant success on risk-sensitive tasks and shown promise in autonomous driving (AD) as well.
Penalized Proximal Policy Optimization for Safe Reinforcement Learning
Safe reinforcement learning aims to learn the optimal policy while satisfying safety constraints, which is essential in real-world applications.
Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
In two typical cross-domain semantic segmentation tasks, i. e., GTA5 to Cityscapes and SYNTHIA to Cityscapes, our method achieves the state-of-the-art segmentation accuracy.
Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning
One of the key challenges in visual Reinforcement Learning (RL) is to learn policies that can generalize to unseen environments.
BTPK-based interpretable method for NER tasks based on Talmudic Public Announcement Logic
In this paper, we propose a novel interpretable method, BTPK (Binary Talmudic Public Announcement Logic model), to help users understand the internal recognition logic of the name entity recognition tasks based on Talmudic Public Announcement Logic.
Hybrid intelligence for dynamic job-shop scheduling with deep reinforcement learning and attention mechanism
The dynamic job-shop scheduling problem (DJSP) is a class of scheduling tasks that specifically consider the inherent uncertainties such as changing order requirements and possible machine breakdown in realistic smart manufacturing settings.
A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning
The integration of Reinforcement Learning (RL) and Evolutionary Algorithms (EAs) aims at simultaneously exploiting the sample efficiency as well as the diversity and robustness of the two paradigms.
HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks
High-order decomposition is a widely used model compression approach towards compact convolutional neural networks (CNNs).
An Open Source Representation for the NYS Electric Grid to Support Power Grid and Market Transition Studies
Under the increasing need to decarbonize energy systems, there is coupled acceleration in connection of distributed and intermittent renewable resources in power grids.
Probability Density Estimation Based Imitation Learning
In general, IL methods can be categorized into Behavioral Cloning (BC) and Inverse Reinforcement Learning (IRL).
CHIP: CHannel Independence-based Pruning for Compact Neural Networks
Filter pruning has been widely used for neural network compression because of its enabled practical acceleration.
Value Penalized Q-Learning for Recommender Systems
To alleviate the action distribution shift problem in extracting RL policy from static trajectories, we propose Value Penalized Q-learning (VPQ), an uncertainty-based offline RL algorithm.
SPARK: co-exploring model SPArsity and low-RanKness for compact neural networks
Based on the observations and outcomes from our analysis, we then propose SPARK, a unified DNN compression framework that can simultaneously capture model SPArsity and low-RanKness in an efficient way.
$$Research on fusion algorithm of multi-attribute decision making and reinforcement learning based on intuitionistic fuzzy number in wargame environment$$
It is also the first time in this field that an algorithm design for intelligent wargaming combines multi-attribute decision making with reinforcement learning.
Method for making multi-attribute decisions in wargames by combining intuitionistic fuzzy numbers with reinforcement learning
Researchers are increasingly focusing on intelligent games as a hot research area. The article proposes an algorithm that combines the multi-attribute management and reinforcement learning methods, and that combined their effect on wargaming, it solves the problem of the agent's low rate of winning against specific rules and its inability to quickly converge during intelligent wargame training. At the same time, this paper studied a multi-attribute decision making and reinforcement learning algorithm in a wargame simulation environment, and obtained data on red and blue conflict. Calculate the weight of each attribute based on the intuitionistic fuzzy number weight calculations.
Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation
In this paper, we present IQ, i. e., interference-aware deep Q-learning, to mitigate catastrophic interference in single-task deep reinforcement learning.
Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework
Notably, on CIFAR-100, with 2. 3X and 2. 4X compression ratios, our models have 1. 96% and 2. 21% higher top-1 accuracy than the original ResNet-20 and ResNet-32, respectively.
Boosting Offline Reinforcement Learning with Residual Generative Modeling
While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected.
Optimization of Service Addition in Multilevel Index Model for Edge Computing
With the development of Edge Computing and Artificial Intelligence (AI) technologies, edge devices are witnessed to generate data at unprecedented volume.
Multi-view Clustering with Deep Matrix Factorization and Global Graph Refinement
Multi-view clustering is an important yet challenging task in machine learning and data mining community.
Inference of cell dynamics on perturbation data using adjoint sensitivity
While there is no analogous ground truth for real life biological systems, this work demonstrates the ability to construct and parameterize a considerable diversity of network models with high predictive ability.
Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure
Although various prior works have been proposed to reduce the RNN model sizes, executing RNN models in resource-restricted environments is still a very challenging problem.
Noise Injection-based Regularization for Point Cloud Processing
In this paper, we, for the first time, perform systematic investigation on noise injection-based regularization for point cloud-domain DNNs.
Doubly Residual Neural Decoder: Towards Low-Complexity High-Performance Channel Decoding
Recently deep neural networks have been successfully applied in channel coding to improve the decoding performance.
NVAE-GAN Based Approach for Unsupervised Time Series Anomaly Detection
In recent studies, Lots of work has been done to solve time series anomaly detection by applying Variational Auto-Encoders (VAEs).
How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?
Experiments show that the proxy can effectively curb the increase of the combined risk when minimizing the source risk and distribution discrepancy.
Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings
Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner.
Towards Playing Full MOBA Games with Deep Reinforcement Learning
However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i. e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes.
Learning from a Complementary-label Source Domain: Theory and Algorithms
We consider two cases of this setting, one is that the source domain only contains complementary-label data (completely complementary unsupervised domain adaptation, CC-UDA), and the other is that the source domain has plenty of complementary-label data and a small amount of true-label data (partly complementary unsupervised domain adaptation, PC-UDA).
Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA).
Local Causal Structure Learning and its Discovery Between Type 2 Diabetes and Bone Mineral Density
To illustrate the importance of prior knowledge, the result of the algorithm without prior knowledge is also investigated.
Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation
To achieve this aim, a previous study has proven an upper bound of the target-domain risk, and the open set difference, as an important term in the upper bound, is used to measure the risk on unknown target data.
Compressing Recurrent Neural Networks Using Hierarchical Tucker Tensor Decomposition
Recurrent Neural Networks (RNNs) have been widely used in sequence analysis and modeling.
Enabling Fast and Universal Audio Adversarial Attack Using Generative Model
These idealized assumptions, however, makes the existing audio adversarial attacks mostly impossible to be launched in a timely fashion in practice (e. g., playing unnoticeable adversarial perturbations along with user's streaming input).
PERMDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices
On the other hand, the recent structured matrix-based approach (i. e., CirCNN) is limited by the relatively complex arithmetic computation (i. e., FFT), less flexible compression ratio, and its inability to fully utilize input sparsity.
Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems
As the popularity of voice user interface (VUI) exploded in recent years, speaker recognition system has emerged as an important medium of identifying a speaker in many security-required applications and services.
Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
Worse, the bad actors found for one graph model severely compromise other models as well.
Embedding Compression with Isotropic Iterative Quantization
Continuous representation of words is a standard component in deep learning-based NLP models.
CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator
In addition, CAG exhibits high transferability across different DNN classifier models in black-box attack scenario by introducing random dropout in the process of generating perturbations.
They Might NOT Be Giants: Crafting Black-Box Adversarial Examples with Fewer Queries Using Particle Swarm Optimization
In this paper, we present AdversarialPSO, a black-box attack that uses fewer queries to create adversarial examples with high success rates.
A Critical Note on the Evaluation of Clustering Algorithms
Experimental evaluation is a major research methodology for investigating clustering algorithms and many other machine learning algorithms.
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.
Representation Learning for Heterogeneous Information Networks via Embedding Events
Network representation learning (NRL) has been widely used to help analyze large-scale networks through mapping original networks into a low-dimensional vector space.
Ranked #1 on
Link Prediction
on IMDb
SGAD: Soft-Guided Adaptively-Dropped Neural Network
Based on the developed guideline and adaptive dropping mechanism, an innovative soft-guided adaptively-dropped (SGAD) neural network is proposed in this paper.
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.
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.
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.
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.
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.
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.
