Search Results for author:
Found 44 papers, 12 papers with code
Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens.
Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splitting
In this paper, we propose SmartSplit, a framework that effectively reduces the memory footprint on the device side while guaranteeing the training progress and model accuracy for heterogeneous FL through model splitting. Towards this end, SmartSplit employs a hierarchical structure to adaptively guide the overall training process.
Real-time Accident Anticipation for Autonomous Driving Through Monocular Depth-Enhanced 3D Modeling
The primary goal of traffic accident anticipation is to foresee potential accidents in real time using dashcam videos, a task that is pivotal for enhancing the safety and reliability of autonomous driving technologies.
CRASH: Crash Recognition and Anticipation System Harnessing with Context-Aware and Temporal Focus Attentions
To capture a wider range of visual cues, we further propose a multi-layer fusion that dynamically computes the temporal dependencies between different scenes and iteratively updates the correlations between different visual features for accurate and timely accident prediction.
When, Where, and What? A Novel Benchmark for Accident Anticipation and Localization with Large Language Models
As autonomous driving systems increasingly become part of daily transportation, the ability to accurately anticipate and mitigate potential traffic accidents is paramount.
SUSTechGAN: Image Generation for Object Recognition in Adverse Conditions of Autonomous Driving
We test the SUSTechGAN and the existing well-known GANs to generate driving images in adverse conditions of rain and night and apply the generated images to retrain object recognition networks.
Less is More: Efficient Brain-Inspired Learning for Autonomous Driving Trajectory Prediction
Accurately and safely predicting the trajectories of surrounding vehicles is essential for fully realizing autonomous driving (AD).
Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning
Federated Learning (FL) enables multiple devices to collaboratively train a shared model while ensuring data privacy.
MFTraj: Map-Free, Behavior-Driven Trajectory Prediction for Autonomous Driving
This paper introduces a trajectory prediction model tailored for autonomous driving, focusing on capturing complex interactions in dynamic traffic scenarios without reliance on high-definition maps.
HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
Through a series of experiments, we have uncovered two critical insights that shed light on the training and parameter inefficiency of LoRA.
Breaking the Memory Wall for Heterogeneous Federated Learning with Progressive Training
In order to preserve the feature representation of each block, we decouple the whole training process into two stages: progressive model shrinking and progressive model growing.
Integrated Sensing and Communication for Edge Inference with End-to-End Multi-View Fusion
Integrated sensing and communication (ISAC) is a promising solution to accelerate edge inference via the dual use of wireless signals.
NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning
Navigating a nonholonomic robot in a cluttered environment requires extremely accurate perception and locomotion for collision avoidance.
World Models for Autonomous Driving: An Initial Survey
In the rapidly evolving landscape of autonomous driving, the capability to accurately predict future events and assess their implications is paramount for both safety and efficiency, critically aiding the decision-making process.
A Cognitive-Based Trajectory Prediction Approach for Autonomous Driving
In autonomous vehicle (AV) technology, the ability to accurately predict the movements of surrounding vehicles is paramount for ensuring safety and operational efficiency.
BAT: Behavior-Aware Human-Like Trajectory Prediction for Autonomous Driving
The ability to accurately predict the trajectory of surrounding vehicles is a critical hurdle to overcome on the journey to fully autonomous vehicles.
GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language Models
In the field of autonomous vehicles (AVs), accurately discerning commander intent and executing linguistic commands within a visual context presents a significant challenge.
Open Set Dandelion Network for IoT Intrusion Detection
The OSDN model performs intrusion knowledge transfer from the knowledge-rich source network intrusion domain to facilitate more accurate intrusion detection for the data-scarce target IoT intrusion domain.
Why semantics matters: A deep study on semantic particle-filtering localization in a LiDAR semantic pole-map
Specifically, semantic segmentation is achieved by a new mask-range transformer network in a mask-classfication paradigm.
Adaptive Bi-Recommendation and Self-Improving Network for Heterogeneous Domain Adaptation-Assisted IoT Intrusion Detection
The ABRSI achieves fine-grained intrusion knowledge transfer via adaptive bi-recommendation matching.
Heterogeneous Domain Adaptation for IoT Intrusion Detection: A Geometric Graph Alignment Approach
In this paper, a Geometric Graph Alignment (GGA) approach is leveraged to mask the geometric heterogeneities between domains for better intrusion knowledge transfer.
Inflected Forms Are Redundant in Question Generation Models
Secondly, we propose to adapt QG as a combination of the following actions in the encode-decoder framework: generating a question word, copying a word from the source sequence or generating a word transformation type.
Toward Efficient Automated Feature Engineering
Specifically, we construct the AFE pipeline based on reinforcement learning setting, where each feature is assigned an agent to perform feature transformation \com{and} selection, and the evaluation score of the produced features in downstream tasks serve as the reward to update the policy.
Joint Semantic Transfer Network for IoT Intrusion Detection
The scenario semantic endows source NI and II domain with characteristics from each other to ease the knowledge transfer process via a confused domain discriminator and categorical distribution knowledge preservation.
PECCO: A Profit and Cost-oriented Computation Offloading Scheme in Edge-Cloud Environment with Improved Moth-flame Optimisation
With the fast growing quantity of data generated by smart devices and the exponential surge of processing demand in the Internet of Things (IoT) era, the resource-rich cloud centres have been utilised to tackle these challenges.
MaskRange: A Mask-classification Model for Range-view based LiDAR Segmentation
To answer this question, we propose a unified mask-classification model, MaskRange, for the range-view based LiDAR semantic and panoptic segmentation.
Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification
However, it is challenging to determine the network resources and road sensor placements for multi-stage training with multi-modal datasets in multi-variant scenarios.
Deep Active Learning with Noise Stability
We provide theoretical analyses by leveraging the small Gaussian noise theory and demonstrate that our method favors a subset with large and diverse gradients.
HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud
In the SRT, we extract the local feature for each point cell.
Learning Disentangled Representation for One-shot Progressive Face Swapping
The disentangled representation module comprises an attribute encoder and an identity encoder, which aims to achieve the disentanglement of the identity and attribute information.
Towards Inadequately Pre-trained Models in Transfer Learning
Based on the contradictory phenomenon between FE and FT that better feature extractor fails to be fine-tuned better accordingly, we conduct comprehensive analyses on features before softmax layer to provide insightful explanations.
Learning Moving-Object Tracking with FMCW LiDAR
In this paper, we propose a learning-based moving-object tracking method utilizing our newly developed LiDAR sensor, Frequency Modulated Continuous Wave (FMCW) LiDAR.
Completion and Augmentation based Spatiotemporal Deep Learning Approach for Short-Term Metro Origin-Destination Matrix Prediction under Limited Observable Data
Due to the delayed effect in latest complete OD flow collection, complex spatiotemporal correlations of OD flows in high dimension, it is more challengeable than other traffic prediction tasks of time series.
Integrated Sensing and Communication from Learning Perspective: An SDP3 Approach
Characterizing the sensing and communication performance tradeoff in integrated sensing and communication (ISAC) systems is challenging in the applications of learning-based human motion recognition.
A Deep Reinforcement Learning Approach for Traffic Signal Control Optimization
Inefficient traffic signal control methods may cause numerous problems, such as traffic congestion and waste of energy.
Incorporating Reachability Knowledge into a Multi-Spatial Graph Convolution Based Seq2Seq Model for Traffic Forecasting
Our main novelties are three aspects: (1) We enrich the spatiotemporal information of model inputs by fusing multi-view features (time, location and traffic states) (2) We build multiple kinds of spatial correlations based on both prior knowledge and data-driven knowledge to improve model performance especially in insufficient or noisy data cases.
Machine Learning-based Orchestration of Containers: A Taxonomy and Future Directions
Containerization is a lightweight application virtualization technology, providing high environmental consistency, operating system distribution portability, and resource isolation.
Federated Noisy Client Learning
Federated learning (FL) collaboratively trains a shared global model depending on multiple local clients, while keeping the training data decentralized in order to preserve data privacy.
One Shot Face Swapping on Megapixels
Extensive experiments demonstrate the superiority of MegaFS and the first megapixel level face swapping database is released for research on DeepFake detection and face image editing in the public domain.
Ranked #8 on
Face Swapping
on FaceForensics++
SMILE: Self-Distilled MIxup for Efficient Transfer LEarning
Performing mixup for transfer learning with pre-trained models however is not that simple, a high capacity pre-trained model with a large fully-connected (FC) layer could easily overfit to the target dataset even with samples-to-labels mixed up.
DEAL: Decremental Energy-Aware Learning in a Federated System
To address the conflict between learning SLO and energy efficiency, we propose DEAL, an energy efficient learning system that saves energy and preserves privacy with a decremental learning design.
CrackFormer: Transformer Network for Fine-Grained Crack Detection
The CrackFormer is composed of novel attention modules in a SegNet-like encoder-decoder architecture.
Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement
Fine-tuning deep neural networks pre-trained on large scale datasets is one of the most practical transfer learning paradigm given limited quantity of training samples.
COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization
Softening labels of training datasets with respect to data representations has been frequently used to improve the training of deep neural networks (DNNs).
