Search Results for author: Xiao Han

Found 22 papers, 7 papers with code

Weakly Supervised Semantic Segmentation with Boundary Exploration

1 code implementation ECCV 2020 Liyi Chen, Weiwei Wu, Chenchen Fu, Xiao Han, Yuntao Zhang

Weakly supervised semantic segmentation with image-level labels has attracted a lot of attention recently because these labels are already available in most datasets.

Weakly-Supervised Semantic Segmentation

Leveraging Bidding Graphs for Advertiser-Aware Relevance Modeling in Sponsored Search

no code implementations Findings (EMNLP) 2021 Shuxian Bi, Chaozhuo Li, Xiao Han, Zheng Liu, Xing Xie, Haizhen Huang, Zengxuan Wen

As the fundamental basis of sponsored search, relevance modeling has attracted increasing attention due to the tremendous practical value.

Pan-cancer computational histopathology reveals tumor mutational burden status through weakly-supervised deep learning

no code implementations7 Apr 2022 Siteng Chen, Jinxi Xiang, Xiyue Wang, Jun Zhang, Sen yang, Junzhou Huang, Wei Yang, Junhua Zheng, Xiao Han

In comparison with the state-of-the-art TMB prediction model from previous publications, our multiscale model achieved better performance over previously reported models.

whole slide images

UIGR: Unified Interactive Garment Retrieval

1 code implementation6 Apr 2022 Xiao Han, Sen He, Li Zhang, Yi-Zhe Song, Tao Xiang

In this paper, we propose a Unified Interactive Garment Retrieval (UIGR) framework to unify TGR and VCR.

HyObscure: Hybrid Obscuring for Privacy-Preserving Data Publishing

no code implementations15 Dec 2021 Xiao Han, Yuncong Yang, Junjie Wu

We then design a novel hybrid protection mechanism called HyObscure, to cross-iteratively optimize the generalization and obfuscation operations for maximum privacy protection under a certain utility guarantee.

Data Valuation for Vertical Federated Learning: An Information-Theoretic Approach

no code implementations15 Dec 2021 Xiao Han, Leye Wang, Junjie Wu

Federated learning (FL) is a promising machine learning paradigm that enables cross-party data collaboration for real-world AI applications in a privacy-preserving and law-regulated way.

Federated Learning

Label Hierarchy Transition: Modeling Class Hierarchies to Enhance Deep Classifiers

no code implementations4 Dec 2021 Renzhen Wang, De Cai, Kaiwen Xiao, Xixi Jia, Xiao Han, Deyu Meng

In this paper, we propose Label Hierarchy Transition, a unified probabilistic framework based on deep learning, to address hierarchical classification.

Classification Multi-class Classification +1

Text-Based Person Search with Limited Data

1 code implementation20 Oct 2021 Xiao Han, Sen He, Li Zhang, Tao Xiang

Firstly, to fully utilize the existing small-scale benchmarking datasets for more discriminative feature learning, we introduce a cross-modal momentum contrastive learning framework to enrich the training data for a given mini-batch.

 Ranked #1 on Text based Person Retrieval on CUHK-PEDES (using extra training data)

Contrastive Learning Cross-Modal Retrieval +4

Label Confusion Learning to Enhance Text Classification Models

1 code implementation9 Dec 2020 Biyang Guo, Songqiao Han, Xiao Han, Hailiang Huang, Ting Lu

LCM can learn label confusion to capture semantic overlap among labels by calculating the similarity between instances and labels during training and generate a better label distribution to replace the original one-hot label vector, thus improving the final classification performance.

Classification General Classification +1

Federated Crowdsensing: Framework and Challenges

no code implementations6 Nov 2020 Leye Wang, Han Yu, Xiao Han

In particular, we first propose a federated crowdsensing framework, which analyzes the privacy concerns of each crowdsensing stage (i. e., task creation, task assignment, task execution, and data aggregation) and discuss how federated learning techniques may take effect.

Federated Learning

Microscope Based HER2 Scoring System

no code implementations15 Sep 2020 Jun Zhang, Kuan Tian, Pei Dong, Haocheng Shen, Kezhou Yan, Jianhua Yao, Junzhou Huang, Xiao Han

Recently, artificial intelligence (AI) has been used in various disease diagnosis to improve diagnostic accuracy and reliability, but the interpretation of diagnosis results is still an open problem.

IEEE 802.11be-Wi-Fi 7: New Challenges and Opportunities

no code implementations27 Jul 2020 Cailian Deng, Xuming Fang, Xiao Han, Xianbin Wang, Li Yan, Rong He, Yan Long, Yuchen Guo

Due to the related stringent requirements, supporting these applications over wireless local area network (WLAN) is far beyond the capabilities of the new WLAN standard -- IEEE 802. 11ax.

Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset

1 code implementation EMNLP (sdp) 2020 Edwin Zhang, Nikhil Gupta, Raphael Tang, Xiao Han, Ronak Pradeep, Kuang Lu, Yue Zhang, Rodrigo Nogueira, Kyunghyun Cho, Hui Fang, Jimmy Lin

We present Covidex, a search engine that exploits the latest neural ranking models to provide information access to the COVID-19 Open Research Dataset curated by the Allen Institute for AI.

SIMPLE: Statistical Inference on Membership Profiles in Large Networks

no code implementations3 Oct 2019 Jianqing Fan, Yingying Fan, Xiao Han, Jinchi Lv

Both tests are of the Hotelling-type statistics based on the rows of empirical eigenvectors or their ratios, whose asymptotic covariance matrices are very challenging to derive and estimate.

Multi-Perspective Neural Architecture for Recommendation System

no code implementations12 Jul 2018 Xiao Han, Chen Yidong, Shi Xiaodong

In one stage, the user and item are represented from multiple perspectives and in each perspective, the representations of user and item put attentions to each other.

Recommendation Systems

Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method

no code implementations24 Apr 2017 Xiao Han

Liver lesion segmentation is an important step for liver cancer diagnosis, treatment planning and treatment evaluation.

Lesion Segmentation Tumor Segmentation

MR-based synthetic CT generation using a deep convolutional neural network method

1 code implementation journal 2017 Xiao Han

Applying a trained model to generate a complete sCT volume for each new patient MR image only took 9 s, which was much faster than the atlas‐based approach.

Transfer Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.