Search Results for author:
Found 16 papers, 6 papers with code
An Element-Wise Weights Aggregation Method for Federated Learning
A central challenge in FL is the effective aggregation of local model weights from disparate and potentially unbalanced participating clients.
PointGrasp: Point Cloud-based Grasping for Tendon-driven Soft Robotic Glove Applications
The proposed pipeline demonstrates an average RMSE of 0. 8 $\pm$ 0. 39 cm for simple and 0. 11 $\pm$ 0. 06 cm for complex geometries.
A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective
In this survey paper, our research indicates that the to-learn data, the learning gradients, and the learned model at different stages all can be manipulated to initiate malicious attacks that range from undermining model performance, reconstructing private local data, and to inserting backdoors.
Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution
The Space-Time Video Super-Resolution (STVSR) task aims to enhance the visual quality of videos, by simultaneously performing video frame interpolation (VFI) and video super-resolution (VSR).
Space-time Video Super-resolution
Video Frame Interpolation
+1
Proximal Policy Optimization Actual Combat: Manipulating Output Tokenizer Length
In this paper, we introduce a simple task designed to employ Gloden as a reward model that validates the effectiveness of PPO and inspires it, primarily explaining the task of utilizing PPO to manipulate the tokenizer length of the output generated by the model.
UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View
In the field of 3D object detection for autonomous driving, the sensor portfolio including multi-modality and single-modality is diverse and complex.
OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
3D Semantic Scene Completion (SSC) can provide dense geometric and semantic scene representations, which can be applied in the field of autonomous driving and robotic systems.
Ranked #13 on
3D Semantic Scene Completion
on SemanticKITTI
Occ^2Net: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions
Image matching is a fundamental and critical task in various visual applications, such as Simultaneous Localization and Mapping (SLAM) and image retrieval, which require accurate pose estimation.
Toward Data Heterogeneity of Federated Learning
Federated learning is a popular paradigm for machine learning.
Self-Supervised Learning for MRI Reconstruction with a Parallel Network Training Framework
Specifically, during model optimization, two subsets are constructed by randomly selecting part of k-space data from the undersampled data and then fed into two parallel reconstruction networks to perform information recovery.
Regression Trees for Cumulative Incidence Functions
In this paper, we develop a novel approach to building regression trees for estimating cumulative incidence curves in a competing risks setting.
Integrating global spatial features in CNN based Hyperspectral/SAR imagery classification
In addition, a dual-branch convolutional neural network (CNN) classification method is designed in combination with the global information to mine the pixel features of the image.
Two-Timescale Channel Estimation for Reconfigurable Intelligent Surface Aided Wireless Communications
Although the mobile RIS-UE channel has to be frequently estimated in a small timescale, the associated pilot overhead is low thanks to its low dimension.
Deep Learning for Beamspace Channel Estimation in Millimeter-Wave Massive MIMO Systems
Specifically, based on the prior information that beamspace channel elements can be modeled by the Gaussian mixture distribution, we first derive a new shrinkage function to refine the AMP algorithm.
Supermassive Black Holes with High Accretion Rates in Active Galactic Nuclei. VIII. Structure of the Broad-Line Region and Mass of the Central Black Hole in Mrk 142
We apply three BLR models with different prescriptions of BLR clouds distributions and find that the best model for fitting the data of Mrk 142 is a two-zone BLR model, consistent with the theoretical BLR model surrounding slim accretion disks.
Astrophysics of Galaxies Instrumentation and Methods for Astrophysics
SAR Target Recognition Using the Multi-aspect-aware Bidirectional LSTM Recurrent Neural Networks
However, there is a limitation in current deep learning based ATR solution that each learning process only handle one SAR image, namely learning the static scattering information, while missing the space-varying information.
