Search Results for author: Li Xiao

Found 47 papers, 13 papers with code

Constructing Uyghur Name Entity Recognition System using Neural Machine Translation Tag Projection

no code implementations CCL 2020 Anwar Azmat, Li Xiao, Yang Yating, Dong Rui, Osman Turghun

Although named entity recognition achieved great success by introducing the neural networks, it is challenging to apply these models to low resource languages including Uyghur while it depends on a large amount of annotated training data.

Machine Translation named-entity-recognition +6

Adapter-dependent Adapter Methylation Assay

no code implementations5 Oct 2024 Jia Zhang, Peng Qi, Li Xiao, Mengxi Yuan, Jun Chuan, Yaling Zeng, Li-mei Lin, Yue Gu, Yan Zhang, Duan-fang Liao, Kai Li

Sensitive and reliable methylation assay is important for oncogentic studies and clinical applications.

Aligning in a Compact Space: Contrastive Knowledge Distillation between Heterogeneous Architectures

no code implementations28 May 2024 Hongjun Wu, Li Xiao, Xingkuo Zhang, Yining Miao

Motivated by this, we propose a Low-Frequency Components-based Contrastive Knowledge Distillation (LFCC) framework that significantly enhances the performance of feature-based distillation between heterogeneous architectures.

Contrastive Learning Knowledge Distillation

QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models

no code implementations14 May 2024 Wei Wang, Zhaowei Li, Qi Xu, Yiqing Cai, Hang Song, Qi Qi, Ran Zhou, Zhida Huang, Tao Wang, Li Xiao

For negative knowledge, we propose an innovative self-adversarial approach that generates low-quality rationales by sampling previous iterations of smaller language models, embracing the idea that one can learn from one's own weaknesses.

Contrastive Learning Denoising +3

SAMDA: Leveraging SAM on Few-Shot Domain Adaptation for Electronic Microscopy Segmentation

no code implementations12 Mar 2024 Yiran Wang, Li Xiao

It has been shown that traditional deep learning methods for electronic microscopy segmentation usually suffer from low transferability when samples and annotations are limited, while large-scale vision foundation models are more robust when transferring between different domains but facing sub-optimal improvement under fine-tuning.

Domain Adaptation Segmentation

Exploring General Intelligence via Gated Graph Transformer in Functional Connectivity Studies

no code implementations18 Jan 2024 Gang Qu, Anton Orlichenko, Junqi Wang, Gemeng Zhang, Li Xiao, Aiying Zhang, Zhengming Ding, Yu-Ping Wang

Functional connectivity (FC) as derived from fMRI has emerged as a pivotal tool in elucidating the intricacies of various psychiatric disorders and delineating the neural pathways that underpin cognitive and behavioral dynamics inherent to the human brain.

Functional Connectivity

Robust Multidimentional Chinese Remainder Theorem for Integer Vector Reconstruction

no code implementations20 Nov 2023 Li Xiao, Haiye Huo, Xiang-Gen Xia

To address this problem, a robust MD Chinese remainder theorem (CRT) was recently proposed for a special class of moduli, where the remaining integer matrices left-divided by a greatest common left divisor (gcld) of all the moduli are pairwise commutative and coprime.

CDR-Adapter: Learning Adapters to Dig Out More Transferring Ability for Cross-Domain Recommendation Models

no code implementations4 Nov 2023 Yanyu Chen, Yao Yao, Wai Kin Victor Chan, Li Xiao, Kai Zhang, Liang Zhang, Yun Ye

In this paper, we present a scalable and efficient paradigm to address data sparsity and cold-start issues in CDR, named CDR-Adapter, by decoupling the original recommendation model from the mapping function, without requiring re-engineering the network structure.

Recommendation Systems Transfer Learning

PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection

no code implementations13 Sep 2023 Hanqing Guo, Guangjing Wang, Yuanda Wang, Bocheng Chen, Qiben Yan, Li Xiao

We significantly enhance the query efficiency and reduce the cost of a successful untargeted and targeted adversarial attack by 93. 1% and 65. 5% compared with the state-of-the-art black-box attacks, using merely ~300 queries (~5 minutes) and ~1, 500 queries (~25 minutes), respectively.

Adversarial Attack

BEVStereo++: Accurate Depth Estimation in Multi-view 3D Object Detection via Dynamic Temporal Stereo

no code implementations9 Apr 2023 Yinhao Li, Jinrong Yang, Jianjian Sun, Han Bao, Zheng Ge, Li Xiao

Bounded by the inherent ambiguity of depth perception, contemporary multi-view 3D object detection methods fall into the performance bottleneck.

3D Object Detection Depth Estimation +2

FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion

1 code implementation27 Oct 2022 Jingyi Li, Weiping tu, Li Xiao

Voice conversion (VC) can be achieved by first extracting source content information and target speaker information, and then reconstructing waveform with these information.

Data Augmentation text annotation +2

Energy-grade double pricing mechanism for a combined heat and power system using the asynchronous dispatch method

no code implementations17 Aug 2022 Xinyi Yi, Ye Guo, Hongbin Sun, Qiuwei Wu, Li Xiao

The problem of heat and electricity pricing in combined heat and power systems regarding the time scales of electricity and heat, as well as thermal energy quality, is studied.

A Multiple Market Trading Mechanism for Electricity, Renewable Energy Certificate and Carbon Emission Right of Virtual Power Plants

no code implementations8 Aug 2022 Zhihong Huang, Ye Guo, Qiuwei Wu, Li Xiao, Hongbin Sun

With the introduction of the inventory mechanism of REC and CER, the profit of the VPP increases and better trading decisions with multiple markets are made under the requirements of renewable portfolio standard (RPS) and carbon emission (CE) quota requirements.

SuperVoice: Text-Independent Speaker Verification Using Ultrasound Energy in Human Speech

no code implementations28 May 2022 Hanqing Guo, Qiben Yan, Nikolay Ivanov, Ying Zhu, Li Xiao, Eric J. Hunter

Our evaluation shows that SUPERVOICE achieves 0. 58% equal error rate in the speaker verification task, it only takes 120 ms for testing an incoming utterance, outperforming all existing speaker verification systems.

Text-Independent Speaker Verification

CCAT-NET: A Novel Transformer Based Semi-supervised Framework for Covid-19 Lung Lesion Segmentation

no code implementations6 Apr 2022 Mingyang Liu, Li Xiao, Huiqin Jiang, Qing He

In this work, we propose a novel network structure that combines CNN and Transformer for the segmentation of COVID-19 lesions.

Lesion Segmentation Segmentation

i-Razor: A Differentiable Neural Input Razor for Feature Selection and Dimension Search in DNN-Based Recommender Systems

1 code implementation1 Apr 2022 Yao Yao, Bin Liu, Haoxun He, Dakui Sheng, Ke Wang, Li Xiao, Huanhuan Cao

Noisy features and inappropriate embedding dimension assignments can deteriorate the performance of recommender systems and introduce unnecessary complexity in model training and online serving.

Click-Through Rate Prediction Feature Engineering +3

Learning Incrementally to Segment Multiple Organs in a CT Image

no code implementations4 Mar 2022 Pengbo Liu, Xia Wang, Mengsi Fan, Hongli Pan, Minmin Yin, Xiaohong Zhu, Dandan Du, Xiaoying Zhao, Li Xiao, Lian Ding, Xingwang Wu, S. Kevin Zhou

In each incremental learning (IL) stage, we lose the access to previous data and annotations, whose knowledge is assumingly captured by the current model, and gain the access to a new dataset with annotations of new organ categories, from which we learn to update the organ segmentation model to include the new organs.

Incremental Learning Organ Segmentation +1

CLS: Cross Labeling Supervision for Semi-Supervised Learning

1 code implementation17 Feb 2022 Yao Yao, Junyi Shen, Jin Xu, Bin Zhong, Li Xiao

Based on FixMatch, where a pseudo label is generated from a weakly-augmented sample to teach the prediction on a strong augmentation of the same input sample, CLS allows the creation of both pseudo and complementary labels to support both positive and negative learning.

Pseudo Label

Knowledge Matters: Radiology Report Generation with General and Specific Knowledge

no code implementations30 Dec 2021 Shuxin Yang, Xian Wu, Shen Ge, Shaohua Kevin Zhou, Li Xiao

In this paper, we propose a knowledge-enhanced radiology report generation approach introduces two types of medical knowledge: 1) General knowledge, which is input independent and provides the broad knowledge for report generation; 2) Specific knowledge, which is input dependent and provides the fine-grained knowledge for report generation.

Decoder General Knowledge +1

IGrow: A Smart Agriculture Solution to Autonomous Greenhouse Control

1 code implementation6 Jul 2021 Xiaoyan Cao, Yao Yao, Lanqing Li, Wanpeng Zhang, Zhicheng An, Zhong Zhang, Li Xiao, Shihui Guo, Xiaoyu Cao, Meihong Wu, Dijun Luo

However, the optimal control of autonomous greenhouses is challenging, requiring decision-making based on high-dimensional sensory data, and the scaling of production is limited by the scarcity of labor capable of handling this task.

Cloud Computing Decision Making

Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation

1 code implementation5 Jul 2021 Yao Yao, Li Xiao, Zhicheng An, Wanpeng Zhang, Dijun Luo

Model-based deep reinforcement learning has achieved success in various domains that require high sample efficiencies, such as Go and robotics.

continuous-control Continuous Control +3

AMA-GCN: Adaptive Multi-layer Aggregation Graph Convolutional Network for Disease Prediction

no code implementations16 Jun 2021 Hao Chen, Fuzhen Zhuang, Li Xiao, Ling Ma, Haiyan Liu, Ruifang Zhang, Huiqin Jiang, Qing He

The encoder can automatically construct the population graph using phenotypic measures which have a positive impact on the final results, and further realizes the fusion of multimodal information.

Disease Prediction text similarity

Incremental Learning for Multi-organ Segmentation with Partially Labeled Datasets

no code implementations8 Mar 2021 Pengbo Liu, Li Xiao, S. Kevin Zhou

In each IL stage, we lose access to the previous annotations, whose knowledge is assumingly captured by the current model, and gain the access to a new dataset with annotations of new organ categories, from which we learn to update the organ segmentation model to include the new organs.

Incremental Learning Organ Segmentation +2

One-Shot Medical Landmark Detection

2 code implementations8 Mar 2021 Qingsong Yao, Quan Quan, Li Xiao, S. Kevin Zhou

The success of deep learning methods relies on the availability of a large number of datasets with annotations; however, curating such datasets is burdensome, especially for medical images.

Self-Supervised Learning

You Only Learn Once: Universal Anatomical Landmark Detection

2 code implementations8 Mar 2021 Heqin Zhu, Qingsong Yao, Li Xiao, S. Kevin Zhou

However, all of those methods are unary in the sense that a highly specialized network is trained for a single task say associated with a particular anatomical region.

Anatomical Landmark Detection Anatomy

Noise Optimization for Artificial Neural Networks

1 code implementation6 Feb 2021 Li Xiao, Zeliang Zhang, Yijie Peng

Adding noises to artificial neural network(ANN) has been shown to be able to improve robustness in previous work.

Ensemble manifold based regularized multi-modal graph convolutional network for cognitive ability prediction

no code implementations20 Jan 2021 Gang Qu, Li Xiao, Wenxing Hu, Kun Zhang, Vince D. Calhoun, Yu-Ping Wang

Methods: To take advantage of complementary information from multi-modal fMRI, we propose an interpretable multi-modal graph convolutional network (MGCN) model, incorporating the fMRI time series and the functional connectivity (FC) between each pair of brain regions.

Functional Connectivity Graph Embedding +1

Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models

1 code implementation16 Dec 2020 Pengbo Liu, Hu Han, Yuanqi Du, Heqin Zhu, Yinhao Li, Feng Gu, Honghu Xiao, Jun Li, Chunpeng Zhao, Li Xiao, Xinbao Wu, S. Kevin Zhou

Due to the lack of a large-scale pelvic CT dataset with annotations, deep learning methods are not fully explored.

G-RCN: Optimizing the Gap between Classification and Localization Tasks for Object Detection

no code implementations14 Nov 2020 Yufan Luo, Li Xiao

By comparing the performance between the original Faster R-CNN and that with partially separated feature maps, we show that: (1) Sharing high-level features for the classification and localization tasks is sub-optimal; (2) Large stride is beneficial for classification but harmful for localization; (3) Global context information could improve the performance of classification.

Classification General Classification +3

Distance Correlation Based Brain Functional Connectivity Estimation and Non-Convex Multi-Task Learning for Developmental fMRI Studies

no code implementations30 Sep 2020 Li Xiao, Biao Cai, Gang Qu, Julia M. Stephen, Tony W. Wilson, Vince D. Calhoun, Yu-Ping Wang

Resting-state functional magnetic resonance imaging (rs-fMRI)-derived functional connectivity patterns have been extensively utilized to delineate global functional organization of the human brain in health, development, and neuropsychiatric disorders.

Connectivity Estimation Functional Connectivity +1

Label-Free Segmentation of COVID-19 Lesions in Lung CT

no code implementations8 Sep 2020 Qingsong Yao, Li Xiao, Peihang Liu, S. Kevin Zhou

Scarcity of annotated images hampers the building of automated solution for reliable COVID-19 diagnosis and evaluation from CT. To alleviate the burden of data annotation, we herein present a label-free approach for segmenting COVID-19 lesions in CT via pixel-level anomaly modeling that mines out the relevant knowledge from normal CT lung scans.

COVID-19 Diagnosis Unsupervised Anomaly Detection

Marginal loss and exclusion loss for partially supervised multi-organ segmentation

no code implementations8 Jul 2020 Gonglei Shi, Li Xiao, Yang Chen, S. Kevin Zhou

Annotating multiple organs in medical images is both costly and time-consuming; therefore, existing multi-organ datasets with labels are often low in sample size and mostly partially labeled, that is, a dataset has a few organs labeled but not all organs.

Organ Segmentation Segmentation

PBRnet: Pyramidal Bounding Box Refinement to Improve Object Localization Accuracy

no code implementations10 Mar 2020 Li Xiao, Yufan Luo, Chunlong Luo, Lianhe Zhao, Quanshui Fu, Guoqing Yang, Anpeng Huang, Yi Zhao

Based on these principles, we designed a novel boundary refinement architecture to improve localization accuracy by combining coarse-to-fine framework with feature pyramid structure, named as Pyramidal Bounding Box Refinement network(PBRnet), which parameterizes gradually focused boundary areas of objects and leverages lower-level feature maps to extract finer local information when refining the predicted bounding boxes.

Object Localization

Learning from Suspected Target: Bootstrapping Performance for Breast Cancer Detection in Mammography

no code implementations1 Mar 2020 Li Xiao, Cheng Zhu, Junjun Liu, Chunlong Luo, Peifang Liu, Yi Zhao

It is worth mention that dense breast typically has a higher risk for developing breast cancers and also are harder for cancer detection in diagnosis, and our method outperforms a reported result from performance of radiologists.

Breast Cancer Detection Medical Image Analysis +3

Training Artificial Neural Networks by Generalized Likelihood Ratio Method: Exploring Brain-like Learning to Improve Robustness

1 code implementation31 Jan 2019 Li Xiao, Yijie Peng, Jeff Hong, Zewu Ke, Shuhuai Yang

In this work, we propose a generalized likelihood ratio method capable of training the artificial neural networks with some biological brain-like mechanisms,. e. g., (a) learning by the loss value, (b) learning via neurons with discontinuous activation and loss functions.

General Classification

Radial Velocity Retrieval for Multichannel SAR Moving Targets with Time-Space Doppler De-ambiguity

no code implementations1 Oct 2016 Jia Xu, Zu-Zhen Huang, Zhi-Rui Wang, Li Xiao, Xiang-Gen Xia, Teng Long

Accordingly, the multichannel SAR systems with different parameters are investigated in three different cases with diverse Doppler ambiguity properties, and a multi-frequency SAR is then proposed to obtain the RV estimation by solving the ambiguity problem based on Chinese remainder theorem (CRT).

Retrieval

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