Search Results for author:
Found 70 papers, 26 papers with code
Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models
Recently, there has been a surge in the development of advanced intelligent generative content (AIGC), especially large language models (LLMs).
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.
Enhancing Human-Computer Interaction in Chest X-ray Analysis using Vision and Language Model with Eye Gaze Patterns
This work proposes a novel approach to enhance human-computer interaction in chest X-ray analysis using Vision-Language Models (VLMs) enhanced with radiologists' attention by incorporating eye gaze data alongside textual prompts.
A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide
Higher-order interactions (HOIs) are ubiquitous in real-world complex systems and applications, and thus investigation of deep learning for HOIs has become a valuable agenda for the data mining and machine learning communities.
Hypergraph-based Multi-View Action Recognition using Event Cameras
By treating segments as vertices and constructing hyperedges using rule-based and KNN-based strategies, a multi-view hypergraph neural network that captures relationships across viewpoint and temporal features is established.
PathoTune: Adapting Visual Foundation Model to Pathological Specialists
As natural image understanding moves towards the pretrain-finetune era, research in pathology imaging is concurrently evolving.
Hyper-3DG: Text-to-3D Gaussian Generation via Hypergraph
Our framework is anchored by a well-established mainflow and an essential module, named ``Geometry and Texture Hypergraph Refiner (HGRefiner)''.
Position Paper: Challenges and Opportunities in Topological Deep Learning
Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models.
LightHGNN: Distilling Hypergraph Neural Networks into MLPs for $100\times$ Faster Inference
Experiments on eight hypergraph datasets demonstrate that even without hypergraph dependency, the proposed LightHGNNs can still achieve competitive or even better performance than HGNNs and outperform vanilla MLPs by $16. 3$ on average.
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.
Improve Robustness of Reinforcement Learning against Observation Perturbations via $l_\infty$ Lipschitz Policy Networks
In this work, we propose a novel robust reinforcement learning method called SortRL, which improves the robustness of DRL policies against observation perturbations from the perspective of the network architecture.
Hypergraph-Guided Disentangled Spectrum Transformer Networks for Near-Infrared Facial Expression Recognition
With the strong robusticity on illumination variations, near-infrared (NIR) can be an effective and essential complement to visible (VIS) facial expression recognition in low lighting or complete darkness conditions.
Facial Expression Recognition
Facial Expression Recognition (FER)
Multi-Energy Guided Image Translation with Stochastic Differential Equations for Near-Infrared Facial Expression Recognition
Illumination variation has been a long-term challenge in real-world facial expression recognition(FER).
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
FedSN: A Novel Federated Learning Framework over LEO Satellite Networks
To this end, we propose FedSN as a general FL framework to tackle the above challenges, and fully explore data diversity on LEO satellites.
NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function
Specifically, we introduce loss functions to facilitate query points to iteratively reach the moving targets and aggregate onto the approximated surface, thereby learning a global surface representation of the data.
Generalized Mixture Model for Extreme Events Forecasting in Time Series Data
Specifically, we propose a Deep Extreme Mixture Model with Autoencoder (DEMMA) for time series prediction.
Human-Producible Adversarial Examples
Visual adversarial examples have so far been restricted to pixel-level image manipulations in the digital world, or have required sophisticated equipment such as 2D or 3D printers to be produced in the physical real world.
SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
Machine Learning (ML) systems are vulnerable to adversarial examples, particularly those from query-based black-box attacks.
Hypergraph Isomorphism Computation
The isomorphism problem is a fundamental problem in network analysis, which involves capturing both low-order and high-order structural information.
Fast, Distribution-free Predictive Inference for Neural Networks with Coverage Guarantees
This paper introduces a novel, computationally-efficient algorithm for predictive inference (PI) that requires no distributional assumptions on the data and can be computed faster than existing bootstrap-type methods for neural networks.
SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds
In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner.
Deep Reinforcement Learning Based Resource Allocation for Cloud Native Wireless Network
Cloud native technology has revolutionized 5G beyond and 6G communication networks, offering unprecedented levels of operational automation, flexibility, and adaptability.
High-Fidelity and Freely Controllable Talking Head Video Generation
Our method leverages both self-supervised learned landmarks and 3D face model-based landmarks to model the motion.
Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks
The increasingly deeper neural networks hinder the democratization of privacy-enhancing distributed learning, such as federated learning (FL), to resource-constrained devices.
LP-DIF: Learning Local Pattern-Specific Deep Implicit Function for 3D Objects and Scenes
To capture geometry details, current mainstream methods divide 3D shapes into local regions and then learn each one with a local latent code via a decoder, where the decoder shares the geometric similarities among different local regions.
Grow and Merge: A Unified Framework for Continuous Categories Discovery
Although a number of studies are devoted to novel category discovery, most of them assume a static setting where both labeled and unlabeled data are given at once for finding new categories.
EasyRec: An easy-to-use, extendable and efficient framework for building industrial recommendation systems
We present EasyRec, an easy-to-use, extendable and efficient recommendation framework for building industrial recommendation systems.
Deep Hypergraph Structure Learning
To address this issue, we design a general paradigm of deep hypergraph structure learning, namely DeepHGSL, to optimize the hypergraph structure for hypergraph-based representation learning.
Distributed Intelligence in Wireless Networks
In this paper, we conduct a comprehensive overview of recent advances in distributed intelligence in wireless networks under the umbrella of native-AI wireless networks, with a focus on the basic concepts of native-AI wireless networks, on the AI-enabled edge computing, on the design of distributed learning architectures for heterogeneous networks, on the communication-efficient technologies to support distributed learning, and on the AI-empowered end-to-end communications.
Lazy Estimation of Variable Importance for Large Neural Networks
Recently, there has been a proliferation of model-agnostic methods to measure variable importance (VI) that analyze the difference in predictive power between a full model trained on all variables and a reduced model that excludes the variable(s) of interest.
3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform
We transform the image feature from a cubemap tile to the Hough space of a Manhattan world and directly map the feature to the geometric output.
3D Room Layouts From A Single RGB Panorama
Room Layout Estimation
On the Limitations of Stochastic Pre-processing Defenses
An example of such a defense is to apply a random transformation to inputs prior to feeding them to the model.
MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet
U-Nets have achieved tremendous success in medical image segmentation.
Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model
In this paper, we introduce a novel method, detection prompt (DetPro), to learn continuous prompt representations for open-vocabulary object detection based on the pre-trained vision-language model.
3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds
To address this problem, we present a novel and efficient self-supervised point cloud representation learning framework, named 3D Occlusion Auto-Encoder (3D-OAE), to facilitate the detailed supervision inherited in local regions and global shapes.
Factored Attention and Embedding for Unstructured-view Topic-related Ultrasound Report Generation
Echocardiography is widely used to clinical practice for diagnosis and treatment, e. g., on the common congenital heart defects.
Towards Language-guided Visual Recognition via Dynamic Convolutions
Based on the LaConv module, we further build the first fully language-driven convolution network, termed as LaConvNet, which can unify the visual recognition and multi-modal reasoning in one forward structure.
Rethinking Supervised Pre-training for Better Downstream Transferring
Though for most cases, the pre-training stage is conducted based on supervised methods, recent works on self-supervised pre-training have shown powerful transferability and even outperform supervised pre-training on multiple downstream tasks.
How Frequency Effect Graph Neural Networks
Based on the frequency principle on GNNs, we present a novel powerful GNNs framework, Multi-Scale Frequency Enhanced Graph Neural Networks (MSF-GNNs) which considers multi-scale representations from wavelet decomposition.
FEATURE-AUGMENTED HYPERGRAPH NEURAL NETWORKS
In FAHGNN, we explore the influence of node features for the expressive power of GNNs and augment features by introducing common features and personal features to model information.
Robust Risk-Sensitive Reinforcement Learning Agents for Trading Markets
Trading markets represent a real-world financial application to deploy reinforcement learning agents, however, they carry hard fundamental challenges such as high variance and costly exploration.
Improved Prediction and Network Estimation Using the Monotone Single Index Multi-variate Autoregressive Model
Network estimation from multi-variate point process or time series data is a problem of fundamental importance.
Relation Modeling in Spatio-Temporal Action Localization
This paper presents our solution to the AVA-Kinetics Crossover Challenge of ActivityNet workshop at CVPR 2021.
Ranked #4 on
Spatio-Temporal Action Localization
on AVA-Kinetics
(using extra training data)
Graph-MLP: Node Classification without Message Passing in Graph
Graph Neural Network (GNN) has been demonstrated its effectiveness in dealing with non-Euclidean structural data.
Aligning Pretraining for Detection via Object-Level Contrastive Learning
Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning.
Leveraging Non-uniformity in First-order Non-convex Optimization
Classical global convergence results for first-order methods rely on uniform smoothness and the \L{}ojasiewicz inequality.
Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
As real-world images come in varying sizes, the machine learning model is part of a larger system that includes an upstream image scaling algorithm.
View-Guided Point Cloud Completion
This paper presents a view-guided solution for the task of point cloud completion.
Ranked #3 on
Point Cloud Completion
on ShapeNet-ViPC
High-Fidelity and Arbitrary Face Editing
However, we observe that the generator tends to find a tricky way to hide information from the original image to satisfy the constraint of cycle consistency, making it impossible to maintain the rich details (e. g., wrinkles and moles) of non-editing areas.
ReCU: Reviving the Dead Weights in Binary Neural Networks
We prove that reviving the "dead weights" by ReCU can result in a smaller quantization error.
Event Stream Super-Resolution via Spatiotemporal Constraint Learning
Therefore, it is imperative to explore the algorithm of event stream super-resolution, which is a non-trivial task due to the sparsity and strong spatio-temporal correlation of the events from an event camera.
Incremental Learning on Growing Graphs
To tackle this problem, we introduce incremental graph learning (IGL), a general framework to formulate the learning on growing graphs in an incremental manner, where traditional graph learning method could be deployed as a basic model.
Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network
The latter contains a Global Adaptive Controller that can adaptively fuse the global information into the decoder to guide the caption generation.
3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection
On KITTI, we are the first to demonstrate semi-supervised 3D object detection and our method surpasses a fully supervised baseline from 1. 8% to 7. 6% under different label ratios and categories.
Self-Supervised Time Series Representation Learning by Inter-Intra Relational Reasoning
In this paper, we present SelfTime: a general self-supervised time series representation learning framework, by exploring the inter-sample relation and intra-temporal relation of time series to learn the underlying structure feature on the unlabeled time series.
Attribute2Font: Creating Fonts You Want From Attributes
To the best of our knowledge, our model is the first one in the literature which is capable of generating glyph images in new font styles, instead of retrieving existing fonts, according to given values of specified font attributes.
Hypergraph Learning for Identification of COVID-19 with CT Imaging
The main challenge in early screening is how to model the confusing cases in the COVID-19 and CAP groups, with very similar clinical manifestations and imaging features.
Multi-agent Reinforcement Learning for Resource Allocation in IoT networks with Edge Computing
To support popular Internet of Things (IoT) applications such as virtual reality, mobile games and wearable devices, edge computing provides a front-end distributed computing archetype of centralized cloud computing with low latency.
Attention-based Multi-modal Fusion Network for Semantic Scene Completion
This paper presents an end-to-end 3D convolutional network named attention-based multi-modal fusion network (AMFNet) for the semantic scene completion (SSC) task of inferring the occupancy and semantic labels of a volumetric 3D scene from single-view RGB-D images.
Ranked #13 on
3D Semantic Scene Completion
on NYUv2
Analyzing Accuracy Loss in Randomized Smoothing Defenses
In test-time attacks an adversary crafts adversarial examples, which are specially crafted perturbations imperceptible to humans which, when added to an input example, force a machine learning model to misclassify the given input example.
Deep Multi-View Enhancement Hashing for Image Retrieval
Therefore, we try to introduce the multi-view deep neural network into the hash learning field, and design an efficient and innovative retrieval model, which has achieved a significant improvement in retrieval performance.
Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning
Extensive experiments on both English and Chinese artistic glyph image datasets demonstrate the superiority of our model in generating high-quality stylized glyph images against other state-of-the-art methods.
Ranked #1 on
Glyph Image Generation
on English Glyph
DHGNN: Dynamic Hypergraph Neural Networks
Then hypergraph convolution is introduced to encode high-order data relations in a hypergraph structure.
Universal Perturbation Attack Against Image Retrieval
In this paper, we make the first attempt in attacking image retrieval systems.
PVRNet: Point-View Relation Neural Network for 3D Shape Recognition
More specifically, based on the relation score module, the point-single-view fusion feature is first extracted by fusing the point cloud feature and each single view feature with point-singe-view relation, then the point-multi-view fusion feature is extracted by fusing the point cloud feature and the features of different number of views with point-multi-view relation.
MeshNet: Mesh Neural Network for 3D Shape Representation
However, there is little effort on using mesh data in recent years, due to the complexity and irregularity of mesh data.
Hypergraph Neural Networks
In this paper, we present a hypergraph neural networks (HGNN) framework for data representation learning, which can encode high-order data correlation in a hypergraph structure.
PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognition
With the recent proliferation of deep learning, various deep models with different representations have achieved the state-of-the-art performance.
GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition
The proposed GVCNN framework is composed of a hierarchical view-group-shape architecture, i. e., from the view level, the group level and the shape level, which are organized using a grouping strategy.
