no code implementations • ACL 2022 • Shuang Liu, Dong Wang, Xiaoguang Li, Minghui Huang, Meizhen Ding
Open-domain question answering is a challenging task with a wide variety of practical applications.
no code implementations • ICCV 2023 • Rabab Abdelfattah, Qing Guo, Xiaoguang Li, XiaoFeng Wang, Song Wang
Using the aggregated similarity scores as the initial pseudo labels at the training stage, we propose an optimization framework to train the parameters of the classification network and refine pseudo labels for unobserved labels.
no code implementations • 26 Jul 2023 • Canyu Zhang, Qing Guo, Xiaoguang Li, Renjie Wan, Hongkai Yu, Ivor Tsang, Song Wang
Given the coordinates of a pixel we want to reconstruct, we first collect its neighboring pixels in the input image and extract their detail-enhanced semantic embeddings, unmask-attentional semantic embeddings, importance values, and spatial distances to the desired pixel.
no code implementations • 21 May 2023 • Xiaoguang Li
To make HSD only focus on the feature of hard samples of dendrite cores, we destroy the structure of the easy samples of dendrites which are detected by ESD and force HSD to learn the feature of hard samples.
no code implementations • 18 May 2023 • Xiaoguang Li, Qing Guo, Pingping Cai, Wei Feng, Ivor Tsang, Song Wang
State-of-the-art shadow removal methods train deep neural networks on collected shadow & shadow-free image pairs, which are desired to complete two distinct tasks via shared weights, i. e., data restoration for shadow regions and identical mapping for non-shadow regions.
1 code implementation • ICCV 2023 • Xiaoguang Li, Qing Guo, Rabab Abdelfattah, Di Lin, Wei Feng, Ivor Tsang, Song Wang
In this work, we find that pretraining shadow removal networks on the image inpainting dataset can reduce the shadow remnants significantly: a naive encoder-decoder network gets competitive restoration quality w. r. t.
no code implementations • 15 Dec 2022 • Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Xin Jiang, Qun Liu, Lei Chen
Disentangled representation learning remains challenging as ground truth factors of variation do not naturally exist.
no code implementations • 20 Oct 2022 • Shaobo Li, Xiaoguang Li, Lifeng Shang, Chengjie Sun, Bingquan Liu, Zhenzhou Ji, Xin Jiang, Qun Liu
Further experiments on question-answering datasets show that trying to learn a deterministic relationship with the proposed methods can also help other knowledge-intensive tasks.
1 code implementation • 18 Oct 2022 • Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin
MIRACL (Multilingual Information Retrieval Across a Continuum of Languages) is a multilingual dataset we have built for the WSDM 2023 Cup challenge that focuses on ad hoc retrieval across 18 different languages, which collectively encompass over three billion native speakers around the world.
no code implementations • Findings (ACL) 2022 • Shaobo Li, Xiaoguang Li, Lifeng Shang, Zhenhua Dong, Chengjie Sun, Bingquan Liu, Zhenzhou Ji, Xin Jiang, Qun Liu
We check the words that have three typical associations with the missing words: knowledge-dependent, positionally close, and highly co-occurred.
1 code implementation • ACL 2022 • Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Lan Luo, Ke Zhan, Enrui Hu, Xinyu Zhang, Hao Jiang, Zhao Cao, Fan Yu, Xin Jiang, Qun Liu, Lei Chen
To alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR).
1 code implementation • CVPR 2022 • Xiaoguang Li, Qing Guo, Di Lin, Ping Li, Wei Feng, Song Wang
As a result, the final method takes the advantage of effective semantic & image-level filling for high-fidelity inpainting.
no code implementations • Findings (ACL) 2022 • Dan Su, Xiaoguang Li, Jindi Zhang, Lifeng Shang, Xin Jiang, Qun Liu, Pascale Fung
Long-form question answering (LFQA) aims to generate a paragraph-length answer for a given question.
Ranked #1 on
Question Answering
on KILT: ELI5
no code implementations • 31 Aug 2021 • Pengfei Zhu, Xiaoguang Li, Jian Li, Hai Zhao
Open-domain Question Answering (ODQA) has achieved significant results in terms of supervised learning manner.
Machine Reading Comprehension
Open-Domain Question Answering
1 code implementation • 9 Jul 2021 • Qing Guo, Xiaoguang Li, Felix Juefei-Xu, Hongkai Yu, Yang Liu, Song Wang
In this paper, for the first time, we formulate image inpainting as a mix of two problems, predictive filtering and deep generation.
no code implementations • 5 Mar 2021 • Chang Liu, Xiaoguang Li, Guohao Cai, Zhenhua Dong, Hong Zhu, Lifeng Shang
It is still an open question to leverage various types of information under the BERT framework.
no code implementations • 31 Dec 2020 • Shaobo Li, Xiaoguang Li, Lifeng Shang, Xin Jiang, Qun Liu, Chengjie Sun, Zhenzhou Ji, Bingquan Liu
In this paper, we propose a new retrieval target, hop, to collect the hidden reasoning evidence from Wikipedia for complex question answering.
Ranked #8 on
Question Answering
on HotpotQA
no code implementations • 1 Nov 2020 • Haonan Yan, Xiaoguang Li, Hui Li, Jiamin Li, Wenhai Sun, Fenghua Li
In MDP, we first propose a novel real-time model extraction status assessment scheme called Monitor to evaluate the situation of the model.
no code implementations • 2 Oct 2020 • Yang Bai, Xiaoguang Li, Gang Wang, Chaoliang Zhang, Lifeng Shang, Jun Xu, Zhaowei Wang, Fangshan Wang, Qun Liu
Term-based sparse representations dominate the first-stage text retrieval in industrial applications, due to its advantage in efficiency, interpretability, and exact term matching.
no code implementations • 19 Aug 2020 • Xiaoguang Li, Feifan Yang, Kin Man Lam, Li Zhuo, Jiafeng Li
Our method can adaptively select the weights of the extracted features according to the spatially varying blur features, and dynamically restore the images.
no code implementations • 28 Jun 2020 • Xiaoguang Li, Peng Fu, Hongxia Yin, ZhenChang Wang, Li Zhuo, HUI ZHANG
Computed Tomography (CT) of the temporal bone has become an important method for diagnosing ear diseases.
no code implementations • 25 May 2020 • Laichuan Shen, Xiaoguang Li, Jing Xia, Lei Qiu, Xichao Zhang, Oleg A. Tretiakov, Motohiko Ezawa, Yan Zhou
Numerical simulations demonstrate that two bimerons with opposite signs of topological numbers can be created simultaneously in a ferromagnetic thin film via current-induced spin torques.
Mesoscale and Nanoscale Physics
no code implementations • 6 Feb 2020 • Xiaoguang Li, Hui Li, Haonan Yan, Zelei Cheng, Wenhai Sun, Hui Zhu
Public intelligent services enabled by machine learning algorithms are vulnerable to model extraction attacks that can steal confidential information of the learning models through public queries.
3 code implementations • 26 Jan 2020 • Pengfei Zhu, Hai Zhao, Xiaoguang Li
Multi-choice Machine Reading Comprehension (MRC) requires model to decide the correct answer from a set of answer options when given a passage and a question.
Ranked #3 on
Reading Comprehension
on RACE
no code implementations • 1 Jan 2020 • Pengfei Zhu, Hai Zhao, Xiaoguang Li
Multi-choice Machine Reading Comprehension (MRC) requires model to decide the correct answer from a set of answer options when given a passage and a question.
no code implementations • 23 Sep 2019 • Wei Cai, Xiaoguang Li, Lizuo Liu
In this paper, we propose a phase shift deep neural network (PhaseDNN), which provides a uniform wideband convergence in approximating high frequency functions and solutions of wave equations.
10 code implementations • 31 Aug 2019 • Junqiu Wei, Xiaozhe Ren, Xiaoguang Li, Wenyong Huang, Yi Liao, Yasheng Wang, Jiashu Lin, Xin Jiang, Xiao Chen, Qun Liu
The pre-trained language models have achieved great successes in various natural language understanding (NLU) tasks due to its capacity to capture the deep contextualized information in text by pre-training on large-scale corpora.
no code implementations • 3 May 2019 • Wei Cai, Xiaoguang Li, Lizuo Liu
Due to the phase shift, each DNN achieves the speed of convergence as in the low frequency range.