no code implementations • 16 May 2024 • Chuan Chen, Tianchi Liao, Xiaojun Deng, Zihou Wu, Sheng Huang, Zibin Zheng
In the field of heterogeneous federated learning (FL), the key challenge is to efficiently and collaboratively train models across multiple clients with different data distributions, model structures, task objectives, computational capabilities, and communication resources.
2 code implementations • 27 Feb 2024 • Wenhao Tang, Fengtao Zhou, Sheng Huang, Xiang Zhu, Yi Zhang, Bo Liu
Unlike existing works that focus on pre-training powerful feature extractor or designing sophisticated instance aggregator, R$^2$T is tailored to re-embed instance features online.
1 code implementation • 18 Feb 2024 • Yijie Wang, Mingjian Hong, Luwen Huangfu, Sheng Huang
To counter this, we introduce an end-to-end generative GZSL framework called D$^3$GZSL.
no code implementations • 3 Aug 2023 • Ziliang Wang, Xiaohong Zhang, Sheng Huang, Wei zhang, Dan Yang, Meng Yan
Quality of Service (QoS) prediction is an essential task in recommendation systems, where accurately predicting unknown QoS values can improve user satisfaction.
1 code implementation • ICCV 2023 • Wenhao Tang, Sheng Huang, Xiaoxian Zhang, Fengtao Zhou, Yi Zhang, Bo Liu
Moreover, the student is used to update the teacher with an exponential moving average (EMA), which in turn identifies new hard instances for subsequent training iterations and stabilizes the optimization.
no code implementations • 28 Mar 2023 • Tao He, Sheng Huang, Wenhao Tang, Bo Liu
DKE employs a segmentation module to segment the shrunken text region as the text kernel, then expands the text kernel contour to obtain text boundary by regressing the vertex-wise offsets.
no code implementations • 4 Dec 2022 • Rong Qin, Luwen Huangfu, Devon Hood, James Ma, Sheng Huang
A light network named the Kernel Inversed Pyramidal Resizing Network (KIPRN) is introduced for image resizing, and can be flexibly plugged into the image classification network as a pre-network to exploit resolution and scale information.
1 code implementation • 21 Sep 2022 • Wenhao Tang, Sheng Huang, Xiaoxian Zhang, Luwen Huangfu
To overcome this drawback, we present a \textit{Patch Refiner} to cluster patches into different groups and only select the highest distress-risk group to yield a slim head for the final image classification.
1 code implementation • 23 May 2022 • Jiazhi Xu, Sheng Huang, Fengtao Zhou, Luwen Huangfu, Daniel Zeng, Bo Liu
Then, the MLIC models of fewer categories are trained with these sub-tasks in parallel for respectively learning the joint patterns and the category-specific patterns of labels.
1 code implementation • 31 Mar 2022 • Sheng Huang, Wenhao Tang, Guixin Huang, Luwen Huangfu, Dan Yang
Specifically, WSPLIN first divides the pavement image under different scales into patches with different collection strategies and then employs a Patch Label Inference Network (PLIN) to infer the labels of these patches to fully exploit the resolution and scale information.
no code implementations • 19 Nov 2021 • Huijun Liu, Chunhua Yang, Ao Li, Sheng Huang, Xin Feng, Zhimin Ruan, Yongxin Ge
In this paper, we propose a Deep Domain Adaptation-based Crack Detection Network (DDACDN), which learns domain invariant features by taking advantage of the source domain knowledge to predict the multi-category crack location information in the target domain, where only image-level labels are available.
no code implementations • 28 Jun 2021 • Yi Zhang, Sheng Huang, Xi Peng, Dan Yang
DCVAE conducts feature synthesis via pairing two Conditional Variational AutoEncoders (CVAEs) with the same seed but different modality conditions in a dizygotic symbiosis manner.
1 code implementation • 2 Apr 2021 • Zeyu Wang, Sheng Huang, Zhongxin Liu, Meng Yan, Xin Xia, Bei Wang, Dan Yang
Considering the lack of technologies in Plot2API, we present a novel deep multi-task learning approach named Semantic Parsing Guided Neural Network (SPGNN) which translates the Plot2API issue as a multi-label image classification and an image semantic parsing tasks for the solution.
1 code implementation • 23 Dec 2020 • Fengtao Zhou, Sheng Huang, Yun Xing
Compared with single-label image classification, multi-label image classification is more practical and challenging.
1 code implementation • 27 May 2020 • Wenhao Tang, Sheng Huang, Qiming Zhao, Ren Li, Luwen Huangfu
We present a novel deep learning framework named the Iteratively Optimized Patch Label Inference Network (IOPLIN) for automatically detecting various pavement distresses that are not solely limited to specific ones, such as cracks and potholes.
1 code implementation • SEMEVAL 2019 • Weimin Lyu, Sheng Huang, Abdul Rafae Khan, Shengqiang Zhang, Weiwei Sun, Jia Xu
This paper describes the systems of the CUNY-PKU team in SemEval 2019 Task 1: Cross-lingual Semantic Parsing with UCCA.
1 code implementation • CONLL 2018 • Yufei Chen, Sheng Huang, Fang Wang, Junjie Cao, Weiwei Sun, Xiaojun Wan
We present experiments for cross-domain semantic dependency analysis with a neural Maximum Subgraph parser.
no code implementations • EMNLP 2017 • Junjie Cao, Sheng Huang, Weiwei Sun, Xiaojun Wan
We propose a new Maximum Subgraph algorithm for first-order parsing to 1-endpoint-crossing, pagenumber-2 graphs.
no code implementations • ACL 2017 • Junjie Cao, Sheng Huang, Weiwei Sun, Xiaojun Wan
We study the Maximum Subgraph problem in deep dependency parsing.
no code implementations • 14 Mar 2016 • Sheng Huang, Dan Yang, Bo Liu, Xiaohong Zhang
Moreover, we plug RH into two conventional hypergraph learning frameworks, namely hypergraph spectral clustering and hypergraph transduction, to present Regression-based Hypergraph Spectral Clustering (RHSC) and Regression-based Hypergraph Transduction (RHT) models for addressing the image clustering and classification issues.
no code implementations • CVPR 2015 • Sheng Huang, Mohamed Elhoseiny, Ahmed Elgammal, Dan Yang
Then the attribute prediction problem is casted as a regularized hypergraph cut problem in which HAP jointly learns a collection of attribute projections from the feature space to a hypergraph embedding space aligned with the attribute space.
no code implementations • 24 Oct 2014 • Sheng Huang, Ahmed Elgammal, Dan Yang
However, many studies on pairwise graphs show that the choice of edge weight can significantly influence the performances of such graph algorithms.
no code implementations • 26 Aug 2014 • Sheng Huang, Dan Yang, Jia Zhou, Luwen Huangfu, Xiaohong Zhang
Then the Laplacian eigenmapping is adopted for deriving the graph Laplacian of the graph.
no code implementations • 28 Dec 2013 • Sheng Huang, Dan Yang, Dong Yang, Ahmed Elgammal
In our algorithm, the discriminating power of DLPP are further exploited from two aspects.
no code implementations • 28 Dec 2013 • Sheng Huang, Dan Yang, Haopeng Zhang, Luwen Huangfu, Xiaohong Zhang
We further exploit the representational power of Haar wavelet and present a novel low-level face representation named Shape Primitives Histogram (SPH) for face recognition.
no code implementations • 6 Nov 2013 • Sheng Huang, Dan Yang, Fei Yang, Yongxin Ge, Xiaohong Zhang, Jiwen Lu
We present an improved Locality Preserving Projections (LPP) method, named Gloablity-Locality Preserving Projections (GLPP), to preserve both the global and local geometric structures of data.