Search Keywords

Results Restricted To:

https://www.temple.edu

Total Results: 34

DRBANET: A Lightweight Dual-Resolution Network for Semantic ...

https://cis.temple.edu/~latecki/Papers/Quan_DRBANET_ICIP_2022.pdf

ABSTRACT Due to the powerful ability to encode image details and semantics, many lightweight dual-resolution networks have been proposed in recent years. However, most of them ignore the benefit of boundary information. This paper introduces a lightweight dual-resolution network, called DRBANet, aim-ing to refine semantic segmentation results with the aid of boundary information. DRBANet also ...

Balancing Privacy and Accuracy using Significant Gradient Protection in ...

https://cis.temple.edu/~wu/research/publications/Publication_files/J-CT-2024-Balancing%20Privacy%20and%20Accuracy%20using%20Siginificant%20Gradient%20Protection%20in%20Federated%20Learning.pdf

Abstract—Previous state-of-the-art studies have demonstrated that adversaries can access sensitive user data by membership inference attacks (MIAs) in Federated Learning (FL). Intro-ducing differential privacy (DP) into the FL framework is an effective way to enhance the privacy of FL. Nevertheless, in differentially private federated learning (DP-FL), local gradients become excessively ...

Joint Dynamic Grouping and Gradient Coding for Time-critical ...

https://cis.temple.edu/~wu/research/publications/Publication_files/Joint%20Dynamic%20Grouping%20and%20Gradient%20Coding%20for%20Time-critical%20Distributed%20Machine%20Learning%20in%20Heterogeneous%20Edge%20Networks-FINAL-VERSION.pdf

Abstract—In edge networks, distributed computing resources have been widely utilized to collaboratively perform a machine learning task by multiple nodes. However, the model training time in heterogeneous edge networks is becoming longer because of excessive computation and delay caused by slow nodes, namely stragglers. The parameter server even abandons stragglers which fail to return ...

Multi-granular spatial-temporal synchronous graph convolutional network ...

https://cis.temple.edu/~jiewu/research/publications/Publication_files/1-s2.0-S0957417424018475-main.pdf

However, due to the diversity and complexity, modeling human actions as general graphs and capturing discriminative spatial–temporal motion patterns is challenging. Besides, the inevitable interference, especially occlusion, impairs the robustness of existing methods that depend on complete skeletons. To solve these problems, we propose a Multi-Granular Spatial-Temporal Synchronous Graph ...