no code implementations • 27 May 2024 • Runzhao Yang, Yinda Chen, Zhihong Zhang, Xiaoyu Liu, Zongren Li, Kunlun He, Zhiwei Xiong, Jinli Suo, Qionghai Dai
In the field of medical image compression, Implicit Neural Representation (INR) networks have shown remarkable versatility due to their flexible compression ratios, yet they are constrained by a one-to-one fitting approach that results in lengthy encoding times.
no code implementations • 27 May 2024 • Mucong Ding, Yuancheng Xu, Tahseen Rabbani, Xiaoyu Liu, Brian Gravelle, Teresa Ranadive, Tai-Ching Tuan, Furong Huang
We aim to generate a synthetic validation dataset so that the validation-performance rankings of the models, with different hyperparameters, on the condensed and original datasets are comparable.
no code implementations • 27 May 2024 • Yinda Chen, Haoyuan Shi, Xiaoyu Liu, Te Shi, Ruobing Zhang, Dong Liu, Zhiwei Xiong, Feng Wu
Autoregressive next-token prediction is a standard pretraining method for large-scale language models, but its application to vision tasks is hindered by the non-sequential nature of image data, leading to cumulative errors.
1 code implementation • 9 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.
no code implementations • 25 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.
no code implementations • 24 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.
no code implementations • 14 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.
no code implementations • 13 Mar 2024 • Jingling Li, Zeyu Tang, Xiaoyu Liu, Peter Spirtes, Kun Zhang, Liu Leqi, Yang Liu
Large language models (LLMs) can easily generate biased and discriminative responses.
no code implementations • 27 Feb 2024 • Xiaoyu Liu, Beitong Zhou, Cheng Cheng
However, CRL is mainly used as a pre-training technique, leading to a complicated multi-stage training pipeline.
no code implementations • 25 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.
1 code implementation • 19 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.
2 code implementations • 12 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.
no code implementations • 7 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.
no code implementations • 13 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.
1 code implementation • 23 Nov 2023 • Wentao Ge, Shunian Chen, Guiming Hardy Chen, Zhihong Chen, Junying Chen, Shuo Yan, Chenghao Zhu, Ziyue Lin, Wenya Xie, Xinyi Zhang, Yichen Chai, Xiaoyu Liu, Dingjie Song, Xidong Wang, Anningzhe Gao, Zhiyi Zhang, Jianquan Li, Xiang Wan, Benyou Wang
Multimodal large language models (MLLMs) (e. g., GPT-4V, LLaVA, and Claude-3) have broadened the scope of AI applications.
no code implementations • 15 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.
2 code implementations • 30 Oct 2023 • Guowei Xu, Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu, Jiaxin Yuan, Pu Hua, Shuzhen Li, Yanjie Ze, Hal Daumé III, Furong Huang, Huazhe Xu
To quantify this inactivity, we adopt dormant ratio as a metric to measure inactivity in the RL agent's network.
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.
6 code implementations • 23 Oct 2023 • Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob, Dinesh Manocha, Tianyi Zhou
Our comprehensive case studies within HallusionBench shed light on the challenges of hallucination and illusion in LVLMs.
Ranked #1 on Visual Question Answering (VQA) on HallusionBench
no code implementations • 29 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.
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).
no code implementations • 31 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.
no code implementations • 20 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.
no code implementations • 19 Aug 2023 • Yinda Chen, Wei Huang, Xiaoyu Liu, Shiyu Deng, Qi Chen, Zhiwei Xiong
Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations.
no code implementations • 10 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.
no code implementations • 10 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.
no code implementations • 3 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.
no code implementations • 16 Jun 2023 • Hao-Wen Dong, Xiaoyu Liu, Jordi Pons, Gautam Bhattacharya, Santiago Pascual, Joan Serrà, Taylor Berg-Kirkpatrick, Julian McAuley
Our results show the effectiveness of the proposed method, and that the pretrained diffusion prior can reduce the modality transfer gap.
no code implementations • 12 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.
1 code implementation • CVPR 2023 • Junyi Li, Zhilu Zhang, Xiaoyu Liu, Chaoyu Feng, Xiaotao Wang, Lei Lei, WangMeng Zuo
And we extend the blind-spot network to a blind-neighborhood network (BNN) for providing supervision on flat areas.
no code implementations • 1 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.
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.
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.
no code implementations • 23 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.
1 code implementation • 20 Oct 2022 • Marcos V. Conde, Radu Timofte, Yibin Huang, Jingyang Peng, Chang Chen, Cheng Li, Eduardo Pérez-Pellitero, Fenglong Song, Furui Bai, Shuai Liu, Chaoyu Feng, Xiaotao Wang, Lei Lei, Yu Zhu, Chenghua Li, Yingying Jiang, Yong A, Peisong Wang, Cong Leng, Jian Cheng, Xiaoyu Liu, Zhicun Yin, Zhilu Zhang, Junyi Li, Ming Liu, WangMeng Zuo, Jun Jiang, Jinha Kim, Yue Zhang, Beiji Zou, Zhikai Zong, Xiaoxiao Liu, Juan Marín Vega, Michael Sloth, Peter Schneider-Kamp, Richard Röttger, Furkan Kınlı, Barış Özcan, Furkan Kıraç, Li Leyi, SM Nadim Uddin, Dipon Kumar Ghosh, Yong Ju Jung
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP).
no code implementations • 30 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.
no code implementations • 18 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.
no code implementations • 2 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.
no code implementations • 23 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.
no code implementations • 8 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.
no code implementations • 15 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.
no code implementations • 29 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.
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.
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.
1 code implementation • 16 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.
Ranked #1 on 3D Instance Segmentation on MitoEM
no code implementations • 9 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.
2 code implementations • 2 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.
Ranked #39 on Video Instance Segmentation on OVIS validation
1 code implementation • 10 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.
1 code implementation • 20 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.
no code implementations • 8 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.
no code implementations • 30 Jun 2019 • Ali Lenjani, Shirley J. Dyke, Ilias Bilionis, Chul Min Yeum, Kenzo Kamiya, Jongseong Choi, Xiaoyu Liu, Arindam G. Chowdhury
A typical post-event reconnaissance mission is conducted by first doing a preliminary survey, followed by a detailed survey.
no code implementations • 27 May 2019 • Hanyuan Hang, Xiaoyu Liu, Ingo Steinwart
We propose an algorithm named best-scored random forest for binary classification problems.
1 code implementation • 16 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.
no code implementations • 8 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).
no code implementations • 22 Aug 2018 • Xiaoyu Liu, Jie Chen, Joel Vaughan, Vijayan Nair, Agus Sudjianto
Interpreting a nonparametric regression model with many predictors is known to be a challenging problem.
1 code implementation • 1 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.