Search Results for author: Xuan Li

Found 22 papers, 5 papers with code

Confidence-Guided Unsupervised Domain Adaptation for Cerebellum Segmentation

no code implementations14 Jun 2022 Xuan Li, Paule-J Toussaint, Alan Evans, Xue Liu

To dispense with the manual annotation requirement, we propose to train a model to adaptively transfer the annotation from the cerebellum on the Allen Brain Human Brain Atlas to the BigBrain in an unsupervised manner, taking into account the different staining and spacing between sections.

Semantic Segmentation Unsupervised Domain Adaptation

Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrieval

1 code implementation21 Apr 2022 Zhiqiang Yuan, Wenkai Zhang, Kun fu, Xuan Li, Chubo Deng, Hongqi Wang, Xian Sun

Our model adapts to multi-scale feature inputs, favors multi-source retrieval methods, and can dynamically filter redundant features.

Text-Image Retrieval

A Diversity-Enhanced and Constraints-Relaxed Augmentation for Low-Resource Classification

no code implementations24 Sep 2021 Guang Liu, Hailong Huang, Yuzhao Mao, Weiguo Gao, Xuan Li, Jianping Shen

Previous studies mostly use a fine-tuned Language Model (LM) to strengthen the constraints but ignore the fact that the potential of diversity could improve the effectiveness of generated data.

Data Augmentation Language Modelling

Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup

1 code implementation EMNLP 2021 Guang Liu, Yuzhao Mao, Hailong Huang, Weiguo Gao, Xuan Li

To address these issues, we propose the Adversarial Mixing Policy (AMP), organized in a min-max-rand formulation, to relax the Locally Linear Constraints in Mixup.

Text Classification

CE-Dedup: Cost-Effective Convolutional Neural Nets Training based on Image Deduplication

no code implementations23 Aug 2021 Xuan Li, Liqiong Chang, Xue Liu

To this end, this paper proposes a framework to assess the impact of the near-duplicate images on CNN training performance, called CE-Dedup.

Image Classification

1213Li at SemEval-2021 Task 6: Detection of Propaganda with Multi-modal Attention and Pre-trained Models

no code implementations SEMEVAL 2021 Peiguang Li, Xuan Li, Xian Sun

This paper presents the solution proposed by the 1213Li team for subtask 3 in SemEval-2021 Task 6: identifying the multiple persuasion techniques used in the multi-modal content of the meme.

Monadic Pavlovian associative learning in a backpropagation-free photonic network

no code implementations30 Nov 2020 James Y. S. Tan, Zengguang Cheng, Xuan Li, Nathan Youngblood, Utku E. Ali, C. David Wright, Wolfram H. P. Pernice, Harish Bhaskaran

We then expand the concept to develop larger-scale supervised learning networks using our monadic Pavlovian photonic hardware, developing a distinct machine-learning framework based on single-element associations and, importantly, using backpropagation-free single-layer weight architectures to approach general learning tasks.

Cross-ethnicity Face Anti-spoofing Recognition Challenge: A Review

no code implementations23 Apr 2020 Ajian Liu, Xuan Li, Jun Wan, Sergio Escalera, Hugo Jair Escalante, Meysam Madadi, Yi Jin, Zhuoyuan Wu, Xiaogang Yu, Zichang Tan, Qi Yuan, Ruikun Yang, Benjia Zhou, Guodong Guo, Stan Z. Li

Although ethnic bias has been verified to severely affect the performance of face recognition systems, it still remains an open research problem in face anti-spoofing.

Face Anti-Spoofing Face Recognition

CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing

no code implementations11 Mar 2020 Ajian Li, Zichang Tan, Xuan Li, Jun Wan, Sergio Escalera, Guodong Guo, Stan Z. Li

Ethnic bias has proven to negatively affect the performance of face recognition systems, and it remains an open research problem in face anti-spoofing.

Face Anti-Spoofing Face Recognition

Hierarchical Context Enhanced Multi-Domain Dialogue System for Multi-domain Task Completion

no code implementations3 Mar 2020 Jingyuan Yang, Guang Liu, Yuzhao Mao, Zhiwei Zhao, Weiguo Gao, Xuan Li, Haiqin Yang, Jianping Shen

Task 1 of the DSTC8-track1 challenge aims to develop an end-to-end multi-domain dialogue system to accomplish complex users' goals under tourist information desk settings.

Lagrangian-Eulerian Multi-Density Topology Optimization with the Material Point Method

2 code implementations2 Mar 2020 Yue Li, Xuan Li, Minchen Li, Yixin Zhu, Bo Zhu, Chenfanfu Jiang

A quadrature-level connectivity graph-based method is adopted to avoid the artificial checkerboard issues commonly existing in multi-resolution topology optimization methods.

Computational Physics Computational Engineering, Finance, and Science Graphics

Static and Dynamic Fusion for Multi-modal Cross-ethnicity Face Anti-spoofing

no code implementations5 Dec 2019 Ajian Liu, Zichang Tan, Xuan Li, Jun Wan, Sergio Escalera, Guodong Guo, Stan Z. Li

Regardless of the usage of deep learning and handcrafted methods, the dynamic information from videos and the effect of cross-ethnicity are rarely considered in face anti-spoofing.

Face Anti-Spoofing

Boosting Image Recognition with Non-differentiable Constraints

no code implementations2 Oct 2019 Xuan Li, Yuchen Lu, Peng Xu, Jizong Peng, Christian Desrosiers, Xue Liu

In this paper, we study the problem of image recognition with non-differentiable constraints.

Inductive Bias

An End-to-end Video Text Detector with Online Tracking

no code implementations20 Aug 2019 Hongyuan Yu, Chengquan Zhang, Xuan Li, Junyu Han, Errui Ding, Liang Wang

Most existing methods attempt to enhance the performance of video text detection by cooperating with video text tracking, but treat these two tasks separately.

The ParallelEye Dataset: Constructing Large-Scale Artificial Scenes for Traffic Vision Research

no code implementations22 Dec 2017 Xuan Li, Kunfeng Wang, Yonglin Tian, Lan Yan, Fei-Yue Wang

As a result, we present a viable implementation pipeline for constructing large-scale artificial scenes for traffic vision research.

Instance Segmentation Object Tracking +2

Training and Testing Object Detectors with Virtual Images

no code implementations22 Dec 2017 Yonglin Tian, Xuan Li, Kunfeng Wang, Fei-Yue Wang

In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data.

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