Search Results for author:
Found 43 papers, 19 papers with code
DME-Driver: Integrating Human Decision Logic and 3D Scene Perception in Autonomous Driving
On the other hand, the generation of accurate control signals relies on precise and detailed environmental perception, which is where 3D scene perception models excel.
Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
We introduce Truth Forest, a method that enhances truthfulness in LLMs by uncovering hidden truth representations using multi-dimensional orthogonal probes.
DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection
Specifically, DMA builds a domain-mixing 3D instance bank for the teacher and student models during training, resulting in aligned data representation.
APBench: A Unified Benchmark for Availability Poisoning Attacks and Defenses
To further evaluate the attack and defense capabilities of these poisoning methods, we have developed a benchmark -- APBench for assessing the efficacy of adversarial poisoning.
GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples
Compared with the full-precision one, the model with the binarization method replaces complex tensor multiplication with simple bit-wise binary operations and represents full-precision model parameters and activations with only 1-bit ones, which potentially solves the problem of model size and computational complexity, respectively.
Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks
In this paper, we introduce the UEraser method, which outperforms current defenses against different types of state-of-the-art unlearnable example attacks through a combination of effective data augmentation policies and loss-maximizing adversarial augmentations.
Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency
When used as a pre-training method, our model can significantly outperform the corresponding fully-supervised baseline with only 1/3 3D labels.
LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object Detection
This setting results in two distinct domain gaps: scenarios and sensors, making it difficult to analyze and evaluate the method accurately.
Efficient Loss Function by Minimizing the Detrimental Effect of Floating-Point Errors on Gradient-Based Attacks
Attackers can deceive neural networks by adding human imperceptive perturbations to their input data; this reveals the vulnerability and weak robustness of current deep-learning networks.
AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models
It can generate UAEs from scratch or conditionally based on reference images.
Adaptive Channel Sparsity for Federated Learning Under System Heterogeneity
Owing to the non-i. i. d.
Flareon: Stealthy any2any Backdoor Injection via Poisoned Augmentation
Open software supply chain attacks, once successful, can exact heavy costs in mission-critical applications.
MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attack
In particular, most ensemble defenses exhibit near or exactly 0% robustness against MORA with $\ell^\infty$ perturbation within 0. 02 on CIFAR-10, and 0. 01 on CIFAR-100.
Semi-supervised 3D Object Detection with Proficient Teachers
To reduce the dependence on large supervision, semi-supervised learning (SSL) based approaches have been proposed.
ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection
Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination.
Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization
The advent of large-scale pre-trained language models has contributed greatly to the recent progress in natural language processing.
Unsupervised Visible-light Images Guided Cross-Spectrum Depth Estimation from Dual-Modality Cameras
Meanwhile, we release a large dual-spectrum depth estimation dataset with visible-light and far-infrared stereo images captured in different scenes to the society.
FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction
Federated learning (FL) allows multiple clients to collectively train a high-performance global model without sharing their private data.
Grounding Commands for Autonomous Vehicles via Layer Fusion with Region-specific Dynamic Layer Attention
In this work, we study the problem of language grounding for autonomous vehicles, which aims to localize a region in a visual scene according to a natural language command from a passenger.
Boosting Active Learning via Improving Test Performance
In this work, we explore such an impact by theoretically proving that selecting unlabeled data of higher gradient norm leads to a lower upper-bound of test loss, resulting in better test performance.
SenseMag: Enabling Low-Cost Traffic Monitoring using Non-invasive Magnetic Sensing
Extensive experiment based on real-word field deployment (on the highways in Shenzhen, China) shows that SenseMag significantly outperforms the existing methods in both classification accuracy and the granularity of vehicle types (i. e., 7 types by SenseMag versus 4 types by the existing work in comparisons).
FedDrop: Trajectory-weighted Dropout for Efficient Federated Learning
Federated learning (FL) enables edge clients to train collaboratively while preserving individual's data privacy.
Noise Stability Regularization for Improving BERT Fine-tuning
The brittleness of this process is often reflected by the sensitivity to random seeds.
Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning
Inefficient traffic control may cause numerous problems such as traffic congestion and energy waste.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
LAFEAT: Piercing Through Adversarial Defenses with Latent Features
In this paper, we show that latent features in certain "robust" models are surprisingly susceptible to adversarial attacks.
Adaptive Consistency Regularization for Semi-Supervised Transfer Learning
To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization that consists of two complementary components: Adaptive Knowledge Consistency (AKC) on the examples between the source and target model, and Adaptive Representation Consistency (ARC) on the target model between labeled and unlabeled examples.
Peer-Assisted Robotic Learning: A Data-Driven Collaborative Learning Approach for Cloud Robotic Systems
Both data and models are shared by robots to the cloud after semantic computing and training locally.
FedCM: A Real-time Contribution Measurement Method for Participants in Federated Learning
Furthermore, we developed federated learning open-source software based on FedCM.
Frontier Detection and Reachability Analysis for Efficient 2D Graph-SLAM Based Active Exploration
We propose an integrated approach to active exploration by exploiting the Cartographer method as the base SLAM module for submap creation and performing efficient frontier detection in the geometrically co-aligned submaps induced by graph optimization.
XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup
While the existing multitask learning algorithms need to run backpropagation over both the source and target datasets and usually consume a higher gradient complexity, XMixup transfers the knowledge from source to target tasks more efficiently: for every class of the target task, XMixup selects the auxiliary samples from the source dataset and augments training samples via the simple mixup strategy.
RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr
RIFLE brings meaningful updates to the weights of deep CNN layers and improves low-level feature learning, while the effects of randomization can be easily converged throughout the overall learning procedure.
How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
Recently, various novel deep learning techniques have been developed to process graph data, called graph neural networks (GNNs).
Multi-Graph Convolutional Network for Relationship-Driven Stock Movement Prediction
However, it is well known that an individual stock price is correlated with prices of other stocks in complex ways.
Pay Attention to Features, Transfer Learn Faster CNNs
Deep convolutional neural networks are now widely deployed in vision applications, but a limited size of training data can restrict their task performance.
Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems with Heterogeneous Sensor Data
Compared with transfer learning and meta-learning, FIL is more suitable to be deployed in cloud robotic systems.
LiDAR Iris for Loop-Closure Detection
In this paper, a global descriptor for a LiDAR point cloud, called LiDAR Iris, is proposed for fast and accurate loop-closure detection.
A Robust Stereo Camera Localization Method with Prior LiDAR Map Constrains
Different from the conventional visual localization system, we design a novel visual optimization model by matching planar information between the LiDAR map and visual image.
Automatic Generation of Multi-precision Multi-arithmetic CNN Accelerators for FPGAs
Furthermore, we show how Tomato produces implementations of networks with various sizes running on single or multiple FPGAs.
Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data
The experimental results demonstrate that FIL is capable of increasing imitation learning of local robots in cloud robotic systems.
Focused Quantization for Sparse CNNs
In ResNet-50, we achieved a 18. 08x CR with only 0. 24% loss in top-5 accuracy, outperforming existing compression methods.
Sitatapatra: Blocking the Transfer of Adversarial Samples
Convolutional Neural Networks (CNNs) are widely used to solve classification tasks in computer vision.
Dynamic Channel Pruning: Feature Boosting and Suppression
Making deep convolutional neural networks more accurate typically comes at the cost of increased computational and memory resources.
Estimation of Passenger Route Choice Pattern Using Smart Card Data for Complex Metro Systems
Nowadays, metro systems play an important role in meeting the urban transportation demand in large cities.
