Search

Your search keyword '"Fan, Hao"' showing total 3,557 results
Start Over Author "Fan, Hao"
3,557 results on '"Fan, Hao"'

65. Differential Attention Orientated Cascade Network for Infrared Small Target Detection

Author

Wenjuan Tang, Qun Dai, and Fan Hao

Subjects
Deep learning, differential attention, feature fusion, infrared small target detection, Ocean engineering, TC1501-1800, Geophysics. Cosmic physics, QC801-809
Abstract

Infrared small target detection from complex backgrounds is increasingly vital for military and civilian fields. Nonetheless, most of the existing methods are too restrictive to portray infrared targets from multidimensional and omnidirectional. In this article, we propose a low-rank differential cascade network (LDCNet) to integrate the physical properties and deep cascade features of infrared images. First, the cascade feature extraction module is designed via a multilevel coplanar cascade encoder–decoder structure, which integrates the deep-level and low-level features of infrared targets and backgrounds. Then, to provide a better understanding of the context capture of the scene, the differential attention mechanism based on the change differential analysis and robust principal component analysis is introduced. Finally, the multilevel feature fusion module is designed to adaptively integrate the spatial and semantic information of different depth feature maps to predict the final detection result. During the research, a new maritime small targets detection dataset is also constructed. Experimental results compared with other related methods on three datasets have demonstrated the effectiveness of LDCNet.

Published
2024
Full Text
View/download PDF

66. Generative Adversarial Differential Analysis for Infrared Small Target Detection

Author

Zongfang Ma, Shuo Pang, and Fan Hao

Subjects
Change detection, generative adversarial network (GAN), image segmentation, infrared small target detection, Ocean engineering, TC1501-1800, Geophysics. Cosmic physics, QC801-809
Abstract

Infrared small target detection refers to the extraction of small targets in a complex, low signal-to-noise ratio background. Depthwise convolution makes it difficult to comprehensively characterize small infrared targets and ignores the importance of image background for the detection task. In this article, we propose the generative adversarial differential analysis (GADA) model for infrared small target detection, the core of which aims to weaken the reliance on target features and enhance the use of background information. Specifically, we first construct pseudobackground labels by the fast marching method. Then, the background-guided generative adversarial network is used to learn the background data distribution. On this basis, the differential image containing interest regions of small targets is obtained by differential analysis. Finally, the detection results are obtained by performing an elaborate characterization of the interest regions. The effectiveness of GADA is verified with three public datasets. Compared to several state-of-the-art methods, GADA achieves better performance in terms of $F1$, $IoU$, and $AUC$.

Published
2024
Full Text
View/download PDF

67. Trans-vaccenic acid reprograms CD8+ T cells and anti-tumour immunity

Author

Fan, Hao, Xia, Siyuan, Xiang, Junhong, Li, Yuancheng, Ross, Matthew O., Lim, Seon Ah, Yang, Fan, Tu, Jiayi, Xie, Lishi, Dougherty, Urszula, Zhang, Freya Q., Zheng, Zhong, Zhang, Rukang, Wu, Rong, Dong, Lei, Su, Rui, Chen, Xiufen, Althaus, Thomas, Riedell, Peter A., Jonker, Patrick B., Muir, Alexander, Lesinski, Gregory B., Rafiq, Sarwish, Dhodapkar, Madhav V., Stock, Wendy, Odenike, Olatoyosi, Patel, Anand A., Opferman, Joseph, Tsuji, Takemasa, Matsuzaki, Junko, Shah, Hardik, Faubert, Brandon, Elf, Shannon E., Layden, Brian, Bissonnette, B. Marc, He, Yu-Ying, Kline, Justin, Mao, Hui, Odunsi, Kunle, Gao, Xue, Chi, Hongbo, He, Chuan, and Chen, Jing

Published
2023
Full Text
View/download PDF

68. Efficient Batch Homomorphic Encryption for Vertically Federated XGBoost

Author

Xu, Wuxing, Fan, Hao, Li, Kaixin, and Yang, Kai

Subjects
Computer Science - Cryptography and Security, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

More and more orgainizations and institutions make efforts on using external data to improve the performance of AI services. To address the data privacy and security concerns, federated learning has attracted increasing attention from both academia and industry to securely construct AI models across multiple isolated data providers. In this paper, we studied the efficiency problem of adapting widely used XGBoost model in real-world applications to vertical federated learning setting. State-of-the-art vertical federated XGBoost frameworks requires large number of encryption operations and ciphertext transmissions, which makes the model training much less efficient than training XGBoost models locally. To bridge this gap, we proposed a novel batch homomorphic encryption method to cut the cost of encryption-related computation and transmission in nearly half. This is achieved by encoding the first-order derivative and the second-order derivative into a single number for encryption, ciphertext transmission, and homomorphic addition operations. The sum of multiple first-order derivatives and second-order derivatives can be simultaneously decoded from the sum of encoded values. We are motivated by the batch idea in the work of BatchCrypt for horizontal federated learning, and design a novel batch method to address the limitations of allowing quite few number of negative numbers. The encode procedure of the proposed batch method consists of four steps, including shifting, truncating, quantizing and batching, while the decoding procedure consists of de-quantization and shifting back. The advantages of our method are demonstrated through theoretical analysis and extensive numerical experiments.

Published
2021

92. Analysis of fluid force and flow fields during gliding in swimming using smoothed particle hydrodynamics method

Author

Meng-Meng Liu, Chuan-Wen Yu, Qing-Hua Meng, Xiao-Fan Hao, Zhi-Long Chen, and Ming He

Subjects
swimming, gliding, fluid force, flow field, smoothed particle hydrodynamics (SPH), numerical analysis, Biotechnology, TP248.13-248.65
Abstract

Gliding is a crucial phase in swimming, yet the understanding of fluid force and flow fields during gliding remains incomplete. This study analyzes gliding through Computational Fluid Dynamics simulations. Specifically, a numerical model based on the Smoothed Particle Hydrodynamics (SPH) method for flow-object interactions is established. Fluid motion is governed by continuity, Navier-Stokes, state, and displacement equations. Modified dynamic boundary particles are used to implement solid boundaries, and steady and uniform flows are generated with inflow and outflow conditions. The reliability of the SPH model is validated by replicating a documented laboratory experiment on a circular cylinder advancing steadily beneath a free surface. Reasonable agreement is observed between the numerical and experimental drag force and lift force. After the validation, the SPH model is employed to analyze the passive drag, vertical force, and pitching moment acting on a streamlined gliding 2D swimmer model as well as the surrounding velocity and vorticity fields, spanning gliding velocities from 1 m/s to 2.5 m/s, submergence depths from 0.2 m to 1 m, and attack angles from −10° to 10°. The results indicate that with the increasing gliding velocity, passive drag and pitching moment increase whereas vertical force decreases. The wake flow and free surface demonstrate signs of instability. Conversely, as the submergence depth increases, there is a decrease in passive drag and pitching moment, accompanied by an increase in vertical force. The undulation of the free surface and its interference in flow fields diminish. With the increase in the attack angle, passive drag and vertical force decrease whereas pitching moment increases, along with the alteration in wake direction and the increasing complexity of the free surface. These outcomes offer valuable insights into gliding dynamics, furnishing swimmers with a scientific basis for selecting appropriate submergence depth and attack angle.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results