Search Results for author: Xiaoyu Liu

Found 52 papers, 17 papers with code

SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions

1 code implementation9 Apr 2024 Xiaoyu Liu, Yuxiang Wei, Ming Liu, Xianhui Lin, Peiran Ren, Xuansong Xie, WangMeng Zuo

The key idea of our SmartControl is to relax the visual condition on the areas that are conflicted with text prompts.

Distilling Semantic Priors from SAM to Efficient Image Restoration Models

no code implementations25 Mar 2024 Quan Zhang, Xiaoyu Liu, Wei Li, Hanting Chen, Junchao Liu, Jie Hu, Zhiwei Xiong, Chun Yuan, Yunhe Wang

SPD leverages a self-distillation manner to distill the fused semantic priors to boost the performance of original IR models.

Deblurring Denoising +2

BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval

no code implementations24 Mar 2024 Yinda Chen, Che Liu, Xiaoyu Liu, Rossella Arcucci, Zhiwei Xiong

The burgeoning integration of 3D medical imaging into healthcare has led to a substantial increase in the workload of medical professionals.

Medical Image Retrieval Retrieval

Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey

no code implementations14 Mar 2024 Xiaoyu Liu, Paiheng Xu, Junda Wu, Jiaxin Yuan, Yifan Yang, YuHang Zhou, Fuxiao Liu, Tianrui Guan, Haoliang Wang, Tong Yu, Julian McAuley, Wei Ai, Furong Huang

Causal inference has shown potential in enhancing the predictive accuracy, fairness, robustness, and explainability of Natural Language Processing (NLP) models by capturing causal relationships among variables.

Causal Inference Fairness

Unmasking and Quantifying Racial Bias of Large Language Models in Medical Report Generation

no code implementations25 Jan 2024 Yifan Yang, Xiaoyu Liu, Qiao Jin, Furong Huang, Zhiyong Lu

Large language models like GPT-3. 5-turbo and GPT-4 hold promise for healthcare professionals, but they may inadvertently inherit biases during their training, potentially affecting their utility in medical applications.

Medical Report Generation

Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences

1 code implementation19 Jan 2024 Xiyao Wang, YuHang Zhou, Xiaoyu Liu, Hongjin Lu, Yuancheng Xu, Feihong He, Jaehong Yoon, Taixi Lu, Gedas Bertasius, Mohit Bansal, Huaxiu Yao, Furong Huang

However, current MLLM benchmarks are predominantly designed to evaluate reasoning based on static information about a single image, and the ability of modern MLLMs to extrapolate from image sequences, which is essential for understanding our ever-changing world, has been less investigated.

Language Modelling Large Language Model

Graph Relation Distillation for Efficient Biomedical Instance Segmentation

2 code implementations12 Jan 2024 Xiaoyu Liu, Yueyi Zhang, Zhiwei Xiong, Wei Huang, Bo Hu, Xiaoyan Sun, Feng Wu

IGD constructs a graph representing instance features and relations, transferring these two types of knowledge by enforcing instance graph consistency.

Instance Segmentation Knowledge Distillation +2

conv_einsum: A Framework for Representation and Fast Evaluation of Multilinear Operations in Convolutional Tensorial Neural Networks

no code implementations7 Jan 2024 Tahseen Rabbani, Jiahao Su, Xiaoyu Liu, David Chan, Geoffrey Sangston, Furong Huang

Modern ConvNets continue to achieve state-of-the-art results over a vast array of vision and image classification tasks, but at the cost of increasing parameters.

Image Classification

CBQ: Cross-Block Quantization for Large Language Models

no code implementations13 Dec 2023 Xin Ding, Xiaoyu Liu, Zhijun Tu, Yun Zhang, Wei Li, Jie Hu, Hanting Chen, Yehui Tang, Zhiwei Xiong, Baoqun Yin, Yunhe Wang

Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs.


Explore Spurious Correlations at the Concept Level in Language Models for Text Classification

no code implementations15 Nov 2023 YuHang Zhou, Paiheng Xu, Xiaoyu Liu, Bang An, Wei Ai, Furong Huang

We find that LMs, when encountering spurious correlations between a concept and a label in training or prompts, resort to shortcuts for predictions.

counterfactual In-Context Learning +2

C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder

1 code implementation NeurIPS 2023 Xiaoyu Liu, Jiaxin Yuan, Bang An, Yuancheng Xu, Yifan Yang, Furong Huang

Representation learning assumes that real-world data is generated by a few semantically meaningful generative factors (i. e., sources of variation) and aims to discover them in the latent space.

Disentanglement Inductive Bias

GASS: Generalizing Audio Source Separation with Large-scale Data

no code implementations29 Sep 2023 Jordi Pons, Xiaoyu Liu, Santiago Pascual, Joan Serrà

Here, we study a single general audio source separation (GASS) model trained to separate speech, music, and sound events in a supervised fashion with a large-scale dataset.

Audio Source Separation Speech Separation

Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition

1 code implementation ICCV 2023 Xiaoyu Liu, Ming Liu, Junyi Li, Shuai Liu, Xiaotao Wang, Lei Lei, WangMeng Zuo

In this paper, we circumvent this issue by presenting a joint framework for both unbounded recommendation of camera view and image composition (i. e., UNIC).

Image Cropping

Semi-Supervised SAR ATR Framework with Transductive Auxiliary Segmentation

no code implementations31 Aug 2023 Chenwei Wang, Xiaoyu Liu, Yulin Huang, Siyi Luo, Jifang Pei, Jianyu Yang, Deqing Mao

The recognition performance of 94. 18\% can be achieved under 20 training samples in each class with simultaneous accurate segmentation results.

Few-Shot Learning Inductive Bias +1

An Entropy-Awareness Meta-Learning Method for SAR Open-Set ATR

no code implementations20 Aug 2023 Chenwei Wang, Siyi Luo, Jifang Pei, Xiaoyu Liu, Yulin Huang, Yin Zhang, Jianyu Yang

In this letter, we propose an entropy-awareness meta-learning method that improves the exclusiveness of feature distribution of known classes which means our method is effective for not only classifying the seen classes but also encountering the unseen other classes.

Meta-Learning Open Set Learning

SAR Target Image Generation Method Using Azimuth-Controllable Generative Adversarial Network

no code implementations10 Aug 2023 Chenwei Wang, Jifang Pei, Xiaoyu Liu, Yulin Huang, Deqing Mao, Yin Zhang, Jianyu Yang

The similarity discriminator can differentiate the generated SAR target images from the real SAR images to ensure the accuracy of the generated, while the azimuth predictor measures the difference of azimuth between the generated and the desired to ensure the azimuth controllability of the generated.

Generative Adversarial Network Image Generation

Global in Local: A Convolutional Transformer for SAR ATR FSL

no code implementations10 Aug 2023 Chenwei Wang, Yulin Huang, Xiaoyu Liu, Jifang Pei, Yin Zhang, Jianyu Yang

Convolutional neural networks (CNNs) have dominated the synthetic aperture radar (SAR) automatic target recognition (ATR) for years.

Few-Shot Learning

Seasonality Based Reranking of E-commerce Autocomplete Using Natural Language Queries

no code implementations3 Aug 2023 Prateek Verma, Shan Zhong, Xiaoyu Liu, Adithya Rajan

Query autocomplete (QAC) also known as typeahead, suggests list of complete queries as user types prefix in the search box.

Natural Language Queries

Dynamically Conservative Self-Driving Planner for Long-Tail Cases

no code implementations12 May 2023 Weitao Zhou, Zhong Cao, Nanshan Deng, Xiaoyu Liu, Kun Jiang, Diange Yang

In this way, the DCP is designed to automatically adjust to be more conservative in low-confidence "long-tail" cases while keeping efficient otherwise.

Towards more precise automatic analysis: a comprehensive survey of deep learning-based multi-organ segmentation

no code implementations1 Mar 2023 Xiaoyu Liu, Linhao Qu, Ziyue Xie, Jiayue Zhao, Yonghong Shi, Zhijian Song

Accurate segmentation of multiple organs of the head, neck, chest, and abdomen from medical images is an essential step in computer-aided diagnosis, surgical navigation, and radiation therapy.

Organ Segmentation Segmentation

A Soma Segmentation Benchmark in Full Adult Fly Brain

1 code implementation CVPR 2023 Xiaoyu Liu, Bo Hu, Mingxing Li, Wei Huang, Yueyi Zhang, Zhiwei Xiong

Finally, we provide quantitative and qualitative benchmark comparisons on the testset to validate the superiority of the proposed method, as well as preliminary statistics of the reconstructed somas in the full adult fly brain from the biological perspective.

Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation

1 code implementation ICCV 2023 Xiaoyu Liu, Wei Huang, Zhiwei Xiong, Shenglong Zhou, Yueyi Zhang, Xuejin Chen, Zheng-Jun Zha, Feng Wu

Sparse instance-level supervision has recently been explored to address insufficient annotation in biomedical instance segmentation, which is easier to annotate crowded instances and better preserves instance completeness for 3D volumetric datasets compared to common semi-supervision. In this paper, we propose a sparsely supervised biomedical instance segmentation framework via cross-representation affinity consistency regularization.

Instance Segmentation Pseudo Label +1

Quantitative Evidence on Overlooked Aspects of Enrollment Speaker Embeddings for Target Speaker Separation

no code implementations23 Oct 2022 Xiaoyu Liu, Xu Li, Joan Serrà

Single channel target speaker separation (TSS) aims at extracting a speaker's voice from a mixture of multiple talkers given an enrollment utterance of that speaker.

Speaker Identification Speaker Separation

Swin-transformer-yolov5 For Real-time Wine Grape Bunch Detection

no code implementations30 Aug 2022 Shenglian Lu, Xiaoyu Liu, Zixaun He, Wenbo Liu, Xin Zhang, Manoj Karkee

Results showed that the proposed Swin-T-YOLOv5 outperformed all other studied models for grape bunch detection, with up to 97% of mean Average Precision (mAP) and 0. 89 of F1-score when the weather was cloudy.

Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis

no code implementations18 Aug 2022 Linhao Qu, Siyu Liu, Xiaoyu Liu, Manning Wang, Zhijian Song

Histopathological images contain abundant phenotypic information and pathological patterns, which are the gold standards for disease diagnosis and essential for the prediction of patient prognosis and treatment outcome.

Representation Learning Self-Supervised Learning +1

Long-Tail Prediction Uncertainty Aware Trajectory Planning for Self-driving Vehicles

no code implementations2 Jul 2022 Weitao Zhou, Zhong Cao, Yunkang Xu, Nanshan Deng, Xiaoyu Liu, Kun Jiang, Diange Yang

To this end, this work proposes a trajectory planner to consider the prediction model uncertainty arising from insufficient data for safer performance.

Autonomous Driving Trajectory Planning

AdaptivePaste: Code Adaptation through Learning Semantics-aware Variable Usage Representations

no code implementations23 May 2022 Xiaoyu Liu, Jinu Jang, Neel Sundaresan, Miltiadis Allamanis, Alexey Svyatkovskiy

This scenario motivates the code adaptation task -- a variant of program repair which aims to adapt variable identifiers in a pasted snippet of code to the surrounding, preexisting source code.

Program Repair

Learning to Reduce False Positives in Analytic Bug Detectors

no code implementations8 Mar 2022 Anant Kharkar, Roshanak Zilouchian Moghaddam, Matthew Jin, Xiaoyu Liu, Xin Shi, Colin Clement, Neel Sundaresan

Due to increasingly complex software design and rapid iterative development, code defects and security vulnerabilities are prevalent in modern software.

Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge

no code implementations15 Nov 2021 Jiyang Qi, Yan Gao, Yao Hu, Xinggang Wang, Xiaoyu Liu, Xiang Bai, Serge Belongie, Alan Yuille, Philip H. S. Torr, Song Bai

To promote the development of occlusion understanding, we collect a large-scale dataset called OVIS for video instance segmentation in the occluded scenario.

Instance Segmentation Object Recognition +3

Tuformer: Data-Driven Design of Expressive Transformer by Tucker Tensor Representation

no code implementations ICLR 2022 Xiaoyu Liu, Jiahao Su, Furong Huang

Guided by tensor diagram representations, we formulate a design space where we can analyze the expressive power of the network structure, providing new directions and possibilities for enhanced performance.

LMSA: Low-relation Mutil-head Self-Attention Mechanism in Visual Transformer

no code implementations29 Sep 2021 JingJie Wang, Xiang Wei, Xiaoyu Liu

By appropriately compressing the dimensions of the self-attention relationship variables, the Transformer network can be more efficient and even perform better.

Image Classification Relation

Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy

no code implementations EMNLP 2021 Colin B. Clement, Shuai Lu, Xiaoyu Liu, Michele Tufano, Dawn Drain, Nan Duan, Neel Sundaresan, Alexey Svyatkovskiy

While there are many efforts to extend the context window, we introduce an architecture-independent approach for leveraging the syntactic hierarchies of source code for incorporating entire file-level context into a fixed-length window.

Code Completion Code Generation +3

Advanced Deep Networks for 3D Mitochondria Instance Segmentation

1 code implementation16 Apr 2021 Mingxing Li, Chang Chen, Xiaoyu Liu, Wei Huang, Yueyi Zhang, Zhiwei Xiong

Mitochondria instance segmentation from electron microscopy (EM) images has seen notable progress since the introduction of deep learning methods.

3D Instance Segmentation Denoising +2

On permutation invariant training for speech source separation

no code implementations9 Feb 2021 Xiaoyu Liu, Jordi Pons

We study permutation invariant training (PIT), which targets at the permutation ambiguity problem for speaker independent source separation models.

Clustering Speaker Separation

Occluded Video Instance Segmentation: A Benchmark

2 code implementations2 Feb 2021 Jiyang Qi, Yan Gao, Yao Hu, Xinggang Wang, Xiaoyu Liu, Xiang Bai, Serge Belongie, Alan Yuille, Philip H. S. Torr, Song Bai

On the OVIS dataset, the highest AP achieved by state-of-the-art algorithms is only 16. 3, which reveals that we are still at a nascent stage for understanding objects, instances, and videos in a real-world scenario.

Instance Segmentation Segmentation +3

Ensemble Wrapper Subsampling for Deep Modulation Classification

1 code implementation10 May 2020 Sharan Ramjee, Shengtai Ju, Diyu Yang, Xiaoyu Liu, Aly El Gamal, Yonina C. Eldar

Subsampling of received wireless signals is important for relaxing hardware requirements as well as the computational cost of signal processing algorithms that rely on the output samples.

Classification feature selection +1

An empirical study of Conv-TasNet

1 code implementation20 Feb 2020 Berkan Kadioglu, Michael Horgan, Xiaoyu Liu, Jordi Pons, Dan Darcy, Vivek Kumar

Furthermore, we offer insights into the generalization capabilities of Conv-TasNet and the potential value of improvements to the encoder/decoder.

Histogram Transform Ensembles for Large-scale Regression

no code implementations8 Dec 2019 Hanyuan Hang, Zhouchen Lin, Xiaoyu Liu, Hongwei Wen

Instead, we apply kernel histogram transforms (KHT) equipped with smoother regressors such as support vector machines (SVMs), and it turns out that both single and ensemble KHT enjoy almost optimal convergence rates.


Best-scored Random Forest Classification

no code implementations27 May 2019 Hanyuan Hang, Xiaoyu Liu, Ingo Steinwart

We propose an algorithm named best-scored random forest for binary classification problems.

Binary Classification Classification +1

Fast Deep Learning for Automatic Modulation Classification

1 code implementation16 Jan 2019 Sharan Ramjee, Shengtai Ju, Diyu Yang, Xiaoyu Liu, Aly El Gamal, Yonina C. Eldar

We then study algorithms to reduce the training time by minimizing the size of the training data set, while incurring a minimal loss in classification accuracy.

Classification General Classification

Dual-label Deep LSTM Dereverberation For Speaker Verification

no code implementations8 Sep 2018 Hao Zhang, Stephen Zahorian, Xiao Chen, Peter Guzewich, Xiaoyu Liu

In this paper, we present a reverberation removal approach for speaker verification, utilizing dual-label deep neural networks (DNNs).

Speaker Verification

Deep Neural Network Architectures for Modulation Classification

1 code implementation1 Dec 2017 Xiaoyu Liu, Diyu Yang, Aly El Gamal

Finally, we introduce a Convolutional Long Short-term Deep Neural Network (CLDNN [4]) to achieve an accuracy of approximately 88. 5% at high SNR.

Classification General Classification

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