Search

Your search keyword '"Yang, Yihan"' showing total 594 results
Start Over Author "Yang, Yihan"
594 results on '"Yang, Yihan"'

2. Samba: Semantic Segmentation of Remotely Sensed Images with State Space Model

Author

Zhu, Qinfeng, Cai, Yuanzhi, Fang, Yuan, Yang, Yihan, Chen, Cheng, Fan, Lei, and Nguyen, Anh

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

High-resolution remotely sensed images pose a challenge for commonly used semantic segmentation methods such as Convolutional Neural Network (CNN) and Vision Transformer (ViT). CNN-based methods struggle with handling such high-resolution images due to their limited receptive field, while ViT faces challenges in handling long sequences. Inspired by Mamba, which adopts a State Space Model (SSM) to efficiently capture global semantic information, we propose a semantic segmentation framework for high-resolution remotely sensed images, named Samba. Samba utilizes an encoder-decoder architecture, with Samba blocks serving as the encoder for efficient multi-level semantic information extraction, and UperNet functioning as the decoder. We evaluate Samba on the LoveDA, ISPRS Vaihingen, and ISPRS Potsdam datasets, comparing its performance against top-performing CNN and ViT methods. The results reveal that Samba achieved unparalleled performance on commonly used remote sensing datasets for semantic segmentation. Our proposed Samba demonstrates for the first time the effectiveness of SSM in semantic segmentation of remotely sensed images, setting a new benchmark in performance for Mamba-based techniques in this specific application. The source code and baseline implementations are available at https://github.com/zhuqinfeng1999/Samba.

Published
2024

10. Protected Data Plane OS Using Memory Protection Keys and Lightweight Activation

Author

Yang, Yihan, Huang, Zhuobin, Kaufmann, Antoine, and Li, Jialin

Subjects
Computer Science - Operating Systems
Abstract

Increasing data center network speed coupled with application requirements for high throughput and low latencies have raised the efficiency bar for network stacks. To reduce substantial kernel overhead in network processing, recent proposals bypass the kernel or implement the stack as user space OS service -- both with performance isolation, security, and resource efficiency trade-offs. We present Tardis, a new network stack architecture that combines the performance and resource efficiency benefits of kernel-bypass and the security and performance enforcement of in-kernel stacks. Tardis runs the OS I/O stack in user-level threads that share both address spaces and kernel threads with applications, avoiding almost all kernel context switch and cross-core communication overheads. To provide sufficient protection, Tardis leverages x86 protection keys (MPK) extension to isolate the I/O stack from application code. And to enforce timely scheduling of network processing and fine-grained performance isolation, Tardis implements lightweight scheduler activations with preemption timers.

Published
2023

18. Multi-Head Online Learning for Delayed Feedback Modeling

Author

Gao, Hui and Yang, Yihan

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

In online advertising, it is highly important to predict the probability and the value of a conversion (e.g., a purchase). It not only impacts user experience by showing relevant ads, but also affects ROI of advertisers and revenue of marketplaces. Unlike clicks, which often occur within minutes after impressions, conversions are expected to happen over a long period of time (e.g., 30 days for online shopping). It creates a challenge, as the true labels are only available after the long delays. Either inaccurate labels (partial conversions) are used, or models are trained on stale data (e.g., from 30 days ago). The problem is more eminent in online learning, which focuses on the live performance on the latest data. In this paper, a novel solution is presented to address this challenge using multi-head modeling. Unlike traditional methods, it directly quantizes conversions into multiple windows, such as day 1, day 2, day 3-7, and day 8-30. A sub-model is trained specifically on conversions within each window. Label freshness is maximally preserved in early models (e.g., day 1 and day 2), while late conversions are accurately utilized in models with longer delays (e.g., day 8-30). It is shown to greatly exceed the performance of known methods in online learning experiments for both conversion rate (CVR) and value per click (VPC) predictions. Lastly, as a general method for delayed feedback modeling, it can be combined with any advanced ML techniques to further improve the performance.

Published
2022

33. Design and Control of a Miniature Soft Robotic Fish Actuated by Artificial Muscles

Author

Tsimbo, Moise, Zhu, Yida, Yang, Yihan, Dong, Erbao, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Yang, Huayong, editor, Liu, Honghai, editor, Zou, Jun, editor, Yin, Zhouping, editor, Liu, Lianqing, editor, Yang, Geng, editor, Ouyang, Xiaoping, editor, and Wang, Zhiyong, editor

Published
2023
Full Text
View/download PDF

37. Intelligent evaluation method for power transmission and transformation quantities based on isolation forest and multi-layer perceptron

Author

ZHANG Bo, YANG Yihan, HU Xiliao, and JIANG Nichang

Subjects
power transmission and transformation quantities, rationality threshold, isolation forest, multi-layer perceptron network, pearson correlation coefficient, ridge regression, permutation feature importance, automated assessment, Electrical engineering. Electronics. Nuclear engineering, TK1-9971
Abstract

To evaluate quantities in power transmission and transformation projects， an intelligent evaluation method of quantity threshold based on isolated forest and multi-layer perceptron is proposed. Firstly， the Pearson correlation coefficient and permutation feature importance are applied to explore the relationship between various quantities and related technical features and select the features. On this basis， a neural network predictive model is trained by using five-year historical data. Aiming at the problem that the historical data may contain a lot of noises， a data rationality selection method based on isolation forest is proposed and the accuracy of using the proposed to evaluate quantities is verified in test set. The case simulation shows that the proposed feature selection method can improve the evaluation accuracy of neural network. At the same time， the proposed method can provide both rough estimation and intelligent evaluation on the rationality of quantities and can automatically evaluate the quantity rationality for promoting the digital transformation of power grid infrastructure.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results