Search Results for author:
Found 39 papers, 6 papers with code
Generative Multi-Agent Collaboration in Embodied AI: A Systematic Review
Embodied multi-agent systems (EMAS) have attracted growing attention for their potential to address complex, real-world challenges in areas such as logistics and robotics.
Hyperbolic Contrastive Learning for Hierarchical 3D Point Cloud Embedding
Hyperbolic spaces allow for more efficient modeling of complex, hierarchical structures, which is particularly beneficial in tasks involving multi-modal data.
PDDFormer: Pairwise Distance Distribution Graph Transformer for Crystal Material Property Prediction
This dynamic behavior disrupts the underlying periodicity of the lattice, making crystal graphs based on static lattice parameters and conventional descriptors discontinuous under even slight perturbations.
Relaxed Rotational Equivariance via $G$-Biases in Vision
Group Equivariant Convolution (GConv) can capture rotational equivariance from original data.
SBDet: A Symmetry-Breaking Object Detector via Relaxed Rotation-Equivariance
Furthermore, we propose a Relaxed Rotation-Equivariant Network (R2Net) as the backbone and further develop the Symmetry-Breaking Object Detector (SBDet) for 2D object detection built upon it.
When Foresight Pruning Meets Zeroth-Order Optimization: Efficient Federated Learning for Low-Memory Devices
Comprehensive experimental results obtained from simulation- and real test-bed-based platforms show that our federated foresight-pruning method not only preserves the ability of the dense model with a memory reduction up to 9x but also boosts the performance of the vanilla BP-Free method with dramatically fewer FLOPs.
Deep Extrinsic Manifold Representation for Vision Tasks
Non-Euclidean data is frequently encountered across different fields, yet there is limited literature that addresses the fundamental challenge of training neural networks with manifold representations as outputs.
Exact Fusion via Feature Distribution Matching for Few-shot Image Generation
In this paper we propose an exact Fusion via Feature Distribution matching Generative Adversarial Network (F2DGAN) for few-shot image generation.
WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
Due to the popularity of Artificial Intelligence (AI) technology, numerous backdoor attacks are designed by adversaries to mislead deep neural network predictions by manipulating training samples and training processes.
Continual Learning via Manifold Expansion Replay
To address this problem, we propose a novel replay strategy called Manifold Expansion Replay (MaER).
CTAGE: Curvature-Based Topology-Aware Graph Embedding for Learning Molecular Representations
Therefore, it is necessary to develop a method for predicting molecular properties that effectively combines spatial structural information while maintaining the simplicity and efficiency of graph neural networks.
Hyperbolic Graph Diffusion Model
In order to simultaneously utilize the data generation capabilities of diffusion models and the ability of hyperbolic embeddings to extract latent hierarchical distributions, we propose a novel graph generation method called, Hyperbolic Graph Diffusion Model (HGDM), which consists of an auto-encoder to encode nodes into successive hyperbolic embeddings, and a DM that operates in the hyperbolic latent space.
Simplicial Message Passing for Chemical Property Prediction
Recently, message-passing Neural networks (MPNN) provide a promising tool for dealing with molecular graphs and have achieved remarkable success in facilitating the discovery and materials design with desired properties.
Is Aggregation the Only Choice? Federated Learning via Layer-wise Model Recombination
To address the above issue, inspired by the observation from a geometric perspective that a well-generalized solution is located in a flat area rather than a sharp area, we propose a novel and heuristic FL paradigm named FedMR (Federated Model Recombination).
Group Equivariant BEV for 3D Object Detection
Experimental results demonstrate that GeqBevNet can extract more rotational equivariant features in the 3D object detection of the actual road scene and improve the performance of object orientation prediction.
Autoencoders with Intrinsic Dimension Constraints for Learning Low Dimensional Image Representations
Motivated by the important role of ID, in this paper, we propose a novel deep representation learning approach with autoencoder, which incorporates regularization of the global and local ID constraints into the reconstruction of data representations.
Multi-scale Geometry-aware Transformer for 3D Point Cloud Classification
At first, the MGT divides point cloud data into patches with multiple scales.
DuEqNet: Dual-Equivariance Network in Outdoor 3D Object Detection for Autonomous Driving
The dual-equivariance of our model can extract the equivariant features at both local and global levels, respectively.
A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold
Although Deep Learning (DL) has achieved success in complex Artificial Intelligence (AI) tasks, it suffers from various notorious problems (e. g., feature redundancy, and vanishing or exploding gradients), since updating parameters in Euclidean space cannot fully exploit the geometric structure of the solution space.
CyclicFL: A Cyclic Model Pre-Training Approach to Efficient Federated Learning
We formally analyze the significance of data consistency between the pre-training and training stages of CyclicFL, showing the limited Lipschitzness of loss for the pre-trained models by CyclicFL.
HierarchyFL: Heterogeneous Federated Learning via Hierarchical Self-Distillation
Federated learning (FL) has been recognized as a privacy-preserving distributed machine learning paradigm that enables knowledge sharing among various heterogeneous artificial intelligence (AIoT) devices through centralized global model aggregation.
Continual Learning for Pose-Agnostic Object Recognition in 3D Point Clouds
Continual Learning aims to learn multiple incoming new tasks continually, and to keep the performance of learned tasks at a consistent level.
FedMR: Fedreated Learning via Model Recombination
Worse still, in each round of FL training, FedAvg dispatches the same initial local models to clients, which can easily result in stuck-at-local-search for optimal global models.
Model-Contrastive Learning for Backdoor Defense
Due to the popularity of Artificial Intelligence (AI) techniques, we are witnessing an increasing number of backdoor injection attacks that are designed to maliciously threaten Deep Neural Networks (DNNs) causing misclassification.
Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation
Due to the prosperity of Artificial Intelligence (AI) techniques, more and more backdoors are designed by adversaries to attack Deep Neural Networks (DNNs). Although the state-of-the-art method Neural Attention Distillation (NAD) can effectively erase backdoor triggers from DNNs, it still suffers from non-negligible Attack Success Rate (ASR) together with lowered classification ACCuracy (ACC), since NAD focuses on backdoor defense using attention features (i. e., attention maps) of the same order.
Learning from Attacks: Attacking Variational Autoencoder for Improving Image Classification
We propose an algorithmic framework that leverages the advantages of the DNNs for data self-expression and task-specific predictions, to improve image classification.
SparGE: Sparse Coding-based Patient Similarity Learning via Low-rank Constraints and Graph Embedding
SparGE measures similarity by jointly sparse coding and graph embedding.
O-ViT: Orthogonal Vision Transformer
Inspired by the tremendous success of the self-attention mechanism in natural language processing, the Vision Transformer (ViT) creatively applies it to image patch sequences and achieves incredible performance.
ViR:the Vision Reservoir
To address these problems, a novel method, namely, Vision Reservoir computing (ViR), is proposed here for image classification, as a parallel to ViT.
Learning Robust and Lightweight Model through Separable Structured Transformations
Learning deep models with both lightweight and robustness is necessary for these equipments.
Couplformer:Rethinking Vision Transformer with Coupling Attention Map
With the development of the self-attention mechanism, the Transformer model has demonstrated its outstanding performance in the computer vision domain.
Boost Neural Networks by Checkpoints
In the experiments, it yields up to 5. 02% higher accuracy over single EfficientNet-B0 on the imbalanced datasets.
Deep Clustering With Intra-class Distance Constraint for Hyperspectral Images
The high dimensionality of hyperspectral images often results in the degradation of clustering performance.
Joint Learning of Discriminative Low-dimensional Image Representations Based on Dictionary Learning and Two-layer Orthogonal Projections
There are some inadequacies in the language description of this paper that require further improvement.
1D-Convolutional Capsule Network for Hyperspectral Image Classification
The complex structure of CNNs results in prohibitive training efforts.
Trace Quotient with Sparsity Priors for Learning Low Dimensional Image Representations
We propose a generic algorithmic framework, which leverages two classic representation learning paradigms, i. e., sparse representation and the trace quotient criterion.
Trace Quotient Meets Sparsity: A Method for Learning Low Dimensional Image Representations
This paper presents an algorithm that allows to learn low dimensional representations of images in an unsupervised manner.
An Adaptive Dictionary Learning Approach for Modeling Dynamical Textures
Video representation is an important and challenging task in the computer vision community.
