Zobrazeno 1 - 10
of 1 327
pro vyhledávání: '"Zheng,Jingjing"'
Autor:
Zheng, Jingjing, Cao, Yankai
In this work, we propose a novel Parameter-Efficient Fine-Tuning (PEFT) approach based on Gaussian Graphical Models (GGMs), marking the first application of GGMs to PEFT tasks, to the best of our knowledge. The proposed method utilizes the $\ell_{2,g
Externí odkaz:
http://arxiv.org/abs/2412.08592
A Novel Defense Against Poisoning Attacks on Federated Learning: LayerCAM Augmented with Autoencoder
Recent attacks on federated learning (FL) can introduce malicious model updates that circumvent widely adopted Euclidean distance-based detection methods. This paper proposes a novel defense strategy, referred to as LayerCAM-AE, designed to counterac
Externí odkaz:
http://arxiv.org/abs/2406.02605
This paper puts forth a new training data-untethered model poisoning (MP) attack on federated learning (FL). The new MP attack extends an adversarial variational graph autoencoder (VGAE) to create malicious local models based solely on the benign loc
Externí odkaz:
http://arxiv.org/abs/2404.15042
Autor:
Tsai, Yu-Ju, Jhang, Jin-Cheng, Zheng, Jingjing, Wang, Wei, Chen, Albert Y. C., Sun, Min, Kuo, Cheng-Hao, Yang, Ming-Hsuan
Inherent ambiguity in layout annotations poses significant challenges to developing accurate 360{\deg} room layout estimation models. To address this issue, we propose a novel Bi-Layout model capable of predicting two distinct layout types. One stops
Externí odkaz:
http://arxiv.org/abs/2404.09993
Recently, numerous tensor singular value decomposition (t-SVD)-based tensor recovery methods have shown promise in processing visual data, such as color images and videos. However, these methods often suffer from severe performance degradation when c
Externí odkaz:
http://arxiv.org/abs/2311.13958
This study aims to solve the over-reliance on the rank estimation strategy in the standard tensor factorization-based tensor recovery and the problem of a large computational cost in the standard t-SVD-based tensor recovery. To this end, we proposes
Externí odkaz:
http://arxiv.org/abs/2305.11458
Monocular depth estimation (MDE) has attracted intense study due to its low cost and critical functions for robotic tasks such as localization, mapping and obstacle detection. Supervised approaches have led to great success with the advance of deep l
Externí odkaz:
http://arxiv.org/abs/2208.00160
The task of grasp pattern recognition aims to derive the applicable grasp types of an object according to the visual information. Current state-of-the-art methods ignore category information of objects which is crucial for grasp pattern recognition.
Externí odkaz:
http://arxiv.org/abs/2205.05218
Autor:
Zheng, Jingjing, Zhang, Xueqian, Liu, Lixiang, Li, Quan, Singh, Leena, Han, Jiaguang, Yan, Fengping, Zhang, Weili
Publikováno v:
J Infrared Milli Terahz Waves (2017)
Using metasurfaces to control the wave propagation at will has been very successful over the broad electromagnetic spectrum in recent years. By encoding specially designed abrupt changes of electromagnetic parameters into metasurfaces, such as phase
Externí odkaz:
http://arxiv.org/abs/2204.00693
Autor:
Wang, Yinglin, Tian, Luling, Zheng, Jingjing, Tan, Yixiao, Li, Yang, Wei, Lecheng, Zhang, Fan, Zhu, Liang
Publikováno v:
In Water Research 1 December 2024 267
