1 code implementation • ACL 2022 • Chang Liu, Chongyang Tao, Jiazhan Feng, Dongyan Zhao
Transferring the knowledge to a small model through distillation has raised great interest in recent years.
no code implementations • CCL 2020 • Chang Liu, Shengxiang Gao, Zhengtao Yu, Yuxin Huang, Congcong You
汉越平行句对抽取是缓解汉越平行语料库数据稀缺的重要方法。平行句对抽取可转换为同一语义空间下的句子相似性分类任务, 其核心在于双语语义空间对齐。传统语义空间对齐方法依赖于大规模的双语平行语料, 越南语作为低资源语言获取大规模平行语料相对困难。针对这个问题本文提出一种利用种子词典进行跨语言双语预训练及Bi-LSTM(Bi-directional Long Short-Term Memory)的汉-越平行句对抽取方法。预训练中仅需要大量的汉越单语和一个汉越种子词典, 通过利用汉越种子词典将汉越双语映射到公共语义空间进行词对齐。再利用Bi-LSTM和CNN(Convolutional Neural Networks)分别提取句子的全局特征和局部特征从而最大化表示汉-越句对之间的语义相关性。实验结果表明, 本文模型在F1得分上提升7. 1%, 优于基线模型。
no code implementations • ACL 2022 • Chang Liu, Xu Tan, Chongyang Tao, Zhenxin Fu, Dongyan Zhao, Tie-Yan Liu, Rui Yan
To enable the chatbot to foresee the dialogue future, we design a beam-search-like roll-out strategy for dialogue future simulation using a typical dialogue generation model and a dialogue selector.
no code implementations • CCL 2020 • Hongrui Wang, Chang Liu, Dong Yu
道德词典资源的建设是人工智能伦理计算的一个研究重点。由于道德行为复杂多样, 现有的英文道德词典分类体系并不完善, 而中文方面目前尚未有相关的词典资源, 理论体系和构建方法仍待探究。针对以上问题, 该文提出了面向人工智能伦理计算的中文道德词典构建任务, 设计了四类标签和四种类型, 得到包含25, 012个词的中文道德词典资源。实验结果表明, 该词典资源不仅能够使机器学会道德知识, 判断词的道德标签和类型, 而且能够为句子级别的道德文本分析提供数据支持。
no code implementations • ICML 2020 • Michael Zhu, Chang Liu, Jun Zhu
Particle-based Variational Inference methods (ParVIs), like Stein Variational Gradient Descent, are nonparametric variational inference methods that optimize a set of particles to best approximate a target distribution.
no code implementations • COLING 2022 • Jiazhan Feng, Chongyang Tao, Zhen Li, Chang Liu, Tao Shen, Dongyan Zhao
In this paper, we propose a reciprocal learning approach to jointly optimize a knowledge retriever and a response ranker for knowledge-grounded response retrieval without ground-truth knowledge labels.
no code implementations • 9 May 2024 • Binxiao Huang, Jason Chun Lok, Chang Liu, Ngai Wong
To exploit the abundant information contained in the input data to output label mapping, our scheme utilizes the network trained from the clean dataset as a trigger generator to produce poisons that significantly raise the success rate of backdoor attacks versus conventional approaches.
no code implementations • 7 May 2024 • Chang Liu, Rebecca Saul, Yihao Sun, Edward Raff, Maya Fuchs, Townsend Southard Pantano, James Holt, Kristopher Micinski
Our results illustrate the practical need for robust corpuses of high-quality Windows PE binaries in training modern learning-based binary analyses.
no code implementations • 6 May 2024 • Weihao Jiang, Chang Liu, Kun He
Specifically, we swap the class (CLS) token and patch tokens between the support and query sets to have the mutual attention, which enables each set to focus on the most useful information.
no code implementations • 1 May 2024 • Yian Zhao, Kehan Li, Zesen Cheng, Pengchong Qiao, Xiawu Zheng, Rongrong Ji, Chang Liu, Li Yuan, Jie Chen
In this work, we introduce Granularity-Controllable Interactive Segmentation (GraCo), a novel approach that allows precise control of prediction granularity by introducing additional parameters to input.
1 code implementation • 22 Apr 2024 • Weijie Wang, Jichao Zhang, Chang Liu, Xia Li, Xingqian Xu, Humphrey Shi, Nicu Sebe, Bruno Lepri
To solve the above problems, we introduce a novel method, UVMap-ID, which is a controllable and personalized UV Map generative model.
no code implementations • 19 Apr 2024 • Chang Liu, Xiaohui Xie, Xinggong Zhang, Yong Cui
The networking field is characterized by its high complexity and rapid iteration, requiring extensive expertise to accomplish network tasks, ranging from network design, configuration, diagnosis and security.
1 code implementation • 17 Apr 2024 • Ziyu Zhou, Wenyuan Shen, Chang Liu
Colorectal cancer (CRC), which frequently originates from initially benign polyps, remains a significant contributor to global cancer-related mortality.
no code implementations • 10 Apr 2024 • Ligen Shi, Chang Liu, Ping Yang, Jun Qiu, Xing Zhao
In spectral CT reconstruction, the basis materials decomposition involves solving a large-scale nonlinear system of integral equations, which is highly ill-posed mathematically.
no code implementations • 30 Mar 2024 • Wenhan Cao, Shiqi Liu, Chang Liu, Zeyu He, Stephen S. -T. Yau, Shengbo Eben Li
In this paper, we find that by adding an additional event that stipulates an inequality condition, we can transform the conditional probability into a special integration that is analogous to convolution.
1 code implementation • 27 Mar 2024 • Qiran Zou, Shangyuan Yuan, Shian Du, Yu Wang, Chang Liu, Yi Xu, Jie Chen, Xiangyang Ji
However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts.
Ranked #8 on Motion Synthesis on HumanML3D
no code implementations • 26 Mar 2024 • Chang Liu, Wei Han, Guangyu Yan, Bowang Zhang, Chunlin Li
The swift response of SCC and two-step perturb-and-observe algorithm mitigate output disturbances, thereby expediting the frequency tuning process.
1 code implementation • 17 Mar 2024 • Shantanu Kodgirwar, Lars Loetgering, Chang Liu, Aleena Joseph, Leona Licht, Daniel S. Penagos Molina, Wilhelm Eschen, Jan Rothhardt, Michael Habeck
Image information is restricted by the dynamic range of the detector, which can be addressed using multi-exposure image fusion (MEF).
no code implementations • 14 Mar 2024 • He Zhang, Chang Liu, Zun Wang, Xinran Wei, Siyuan Liu, Nanning Zheng, Bin Shao, Tie-Yan Liu
This merit addresses the data scarcity difficulty, and distinguishes the task from other property prediction formulations with unique benefits: (1) self-consistency training enables the model to be trained on a large amount of unlabeled data, hence substantially enhances generalization; (2) self-consistency training is more efficient than labeling data with DFT for supervised training, since it is an amortization of DFT calculation over a set of molecular structures.
1 code implementation • 11 Mar 2024 • Pengchong Qiao, Lei Shang, Chang Liu, Baigui Sun, Xiangyang Ji, Jie Chen
In this paper, motivated by object-oriented programming, we model the subject as a derived class whose base class is its semantic category.
no code implementations • 5 Mar 2024 • Chang Liu, Fuxin Fan, Annette Schwarz, Andreas Maier
Multi-organ segmentation in medical images is a widely researched task and can save much manual efforts of clinicians in daily routines.
no code implementations • 29 Feb 2024 • Ji Ma, Hongming Dai, Yao Mu, Pengying Wu, Hao Wang, Xiaowei Chi, Yang Fei, Shanghang Zhang, Chang Liu
Zero-Shot Object Navigation (ZSON) requires agents to autonomously locate and approach unseen objects in unfamiliar environments and has emerged as a particularly challenging task within the domain of Embodied AI.
no code implementations • 23 Feb 2024 • Jingtao Ding, Chang Liu, Yu Zheng, Yunke Zhang, Zihan Yu, Ruikun Li, Hongyi Chen, Jinghua Piao, Huandong Wang, Jiazhen Liu, Yong Li
Complex networks pervade various real-world systems, from the natural environment to human societies.
no code implementations • 22 Feb 2024 • Yanliang Huang, Liguo Zhou, Chang Liu, Alois Knoll
The implementation of Autonomous Driving (AD) technologies within urban environments presents significant challenges.
no code implementations • 23 Jan 2024 • Chang Liu, Laura Klein, Yixing Huang, Edith Baader, Michael Lell, Marc Kachelrieß, Andreas Maier
The average organ dice of the proposed method is 0. 71 compared with 0. 63 in baseline model, indicating the enhancement of anatomical structures.
no code implementations • 21 Jan 2024 • Ruochi Zhang, Haoran Wu, Chang Liu, Huaping Li, Yuqian Wu, Kewei Li, Yifan Wang, Yifan Deng, Jiahui Chen, Fengfeng Zhou, Xin Gao
This study introduces a novel multi-view contrastive learning framework PepHarmony for the sequence-based peptide encoding task.
no code implementations • 20 Jan 2024 • Chang Liu, Antwan D. Clark
Constant gain least-mean-squares (LMS) algorithms have a wide range of applications in trajectory tracking problems, but the formal convergence of LMS in mean square is not yet fully established.
1 code implementation • 18 Jan 2024 • Zesen Cheng, Kehan Li, Hao Li, Peng Jin, Chang Liu, Xiawu Zheng, Rongrong Ji, Jie Chen
To mold instance queries to follow Brownian bridge and accomplish alignment with class texts, we design Bridge-Text Alignment (BTA) to learn discriminative bridge-level representations of instances via contrastive objectives.
no code implementations • 5 Jan 2024 • Pengying Wu, Yao Mu, Bingxian Wu, Yi Hou, Ji Ma, Shanghang Zhang, Chang Liu
In the realm of household robotics, the Zero-Shot Object Navigation (ZSON) task empowers agents to adeptly traverse unfamiliar environments and locate objects from novel categories without prior explicit training.
no code implementations • 28 Dec 2023 • Jason Chun Lok Li, Chang Liu, Binxiao Huang, Ngai Wong
Existing approaches to Implicit Neural Representation (INR) can be interpreted as a global scene representation via a linear combination of Fourier bases of different frequencies.
no code implementations • 14 Dec 2023 • Stephen Wu, Yu Otake, Daijiro Mizutani, Chang Liu, Kotaro Asano, Nana Sato, Hidetoshi Baba, Yusuke Fukunaga, Yosuke Higo, Akiyoshi Kamura, Shinnosuke Kodama, Masataka Metoki, Tomoka Nakamura, Yuto Nakazato, Taiga Saito, Akihiro Shioi, Masahiro Takenobu, Keigo Tsukioka, Ryo Yoshikawa
The integration of Large Language Models (LLMs) like ChatGPT into the workflows of geotechnical engineering has a high potential to transform how the discipline approaches problem-solving and decision-making.
no code implementations • 11 Dec 2023 • Yitong Wang, Chang Liu, Jun Zhao
In pursuit of enhancing the accessibility of AIGC services, the deployment of AIGC models (e. g., diffusion models) to edge servers and local devices has become a prevailing trend.
no code implementations • 7 Dec 2023 • Ruyi Gan, XiaoJun Wu, Junyu Lu, Yuanhe Tian, Dixiang Zhang, Ziwei Wu, Renliang Sun, Chang Liu, Jiaxing Zhang, Pingjian Zhang, Yan Song
However, there are few specialized models in certain domains, such as interior design, which is attributed to the complex textual descriptions and detailed visual elements inherent in design, alongside the necessity for adaptable resolution.
no code implementations • 6 Dec 2023 • Chang Liu, Tamas Sziranyi
Taking the Chongqing wildfire on August 24, 2022, as a case study, the results demonstrate that the dynamic escape route planning algorithm can provide an optimal real-time navigation path for humans in the presence of fire through the information fusion of UAVs and satellites.
no code implementations • 6 Dec 2023 • Chang Liu, Tamas Sziranyi
This work focuses on the development of an optimal wildfire escape route planning system specifically designed for drones, considering dynamic fire and smoke models.
1 code implementation • 5 Dec 2023 • Hao Li, Curise Jia, Peng Jin, Zesen Cheng, Kehan Li, Jialu Sui, Chang Liu, Li Yuan
In this paper, we propose the Style-Diversified Query-Based Image Retrieval task, which enables retrieval based on various query styles.
1 code implementation • 5 Dec 2023 • Zhuo Huang, Chang Liu, Yinpeng Dong, Hang Su, Shibao Zheng, Tongliang Liu
Concretely, by estimating a transition matrix that captures the probability of one class being confused with another, an instruction containing a correct exemplar and an erroneous one from the most probable noisy class can be constructed.
no code implementations • 4 Dec 2023 • Akshay Goel, Almog Gueta, Omry Gilon, Chang Liu, Sofia Erell, Lan Huong Nguyen, Xiaohong Hao, Bolous Jaber, Shashir Reddy, Rupesh Kartha, Jean Steiner, Itay Laish, Amir Feder
The results highlight the potential of using LLMs to improve the utilization of unstructured clinical data, allowing for the swift deployment of tailored NLP solutions in healthcare.
no code implementations • 29 Nov 2023 • Chang Liu, Peng Hou, AnXiang Zeng, Han Yu
Since its deployment in March 2023, it has achieved a remarkable 9. 90% increase in terms of clicks per user and a 4. 23% boost in terms of orders per user for the image search feature on the Shopee e-commerce platform.
1 code implementation • 27 Nov 2023 • Aiyu Cui, Jay Mahajan, Viraj Shah, Preeti Gomathinayagam, Chang Liu, Svetlana Lazebnik
By contrast, it is hard to collect paired data for in-the-wild scenes, and therefore, virtual try-on for casual images of people with more diverse poses against cluttered backgrounds is rarely studied.
Ranked #1 on Virtual Try-on on StreetTryOn
1 code implementation • 23 Nov 2023 • Chang Liu, Yuanhe Tian, Yan Song
Specifically, we firstly cover pivotal RRG approaches based on the task-specific features of radiographs, reports, and the cross-modal relations between them, and then illustrate the benchmark datasets conventionally used for this task with evaluation metrics, subsequently analyze the performance of different approaches and finally offer our summary on the challenges and the trends in future directions.
1 code implementation • 14 Nov 2023 • Jinpei Guo, Shaofeng Zhang, Runzhong Wang, Chang Liu, Junchi Yan
Meanwhile, on Pascal VOC, QueryTrans improves the accuracy of NGMv2 from $80. 1\%$ to $\mathbf{83. 3\%}$, and BBGM from $79. 0\%$ to $\mathbf{84. 5\%}$.
Ranked #1 on Graph Matching on PASCAL VOC (matching accuracy metric)
no code implementations • 26 Oct 2023 • Chang Liu, Liguo Zhou, Yanliang Huang, Alois Knoll
Vehicle perception systems strive to achieve comprehensive and rapid visual interpretation of their surroundings for improved safety and navigation.
no code implementations • 2 Oct 2023 • Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang
This study utilizes the intricate Avalon game as a testbed to explore LLMs' potential in deceptive environments.
no code implementations • 28 Sep 2023 • He Zhang, Siyuan Liu, Jiacheng You, Chang Liu, Shuxin Zheng, Ziheng Lu, Tong Wang, Nanning Zheng, Bin Shao
Orbital-free density functional theory (OFDFT) is a quantum chemistry formulation that has a lower cost scaling than the prevailing Kohn-Sham DFT, which is increasingly desired for contemporary molecular research.
no code implementations • 19 Sep 2023 • Chang Liu, Yi Niu, Mingming Ma, Fu Li, Guangming Shi
The basic principle of the patch-matching based style transfer is to substitute the patches of the content image feature maps by the closest patches from the style image feature maps.
no code implementations • 19 Sep 2023 • Chang Liu, Giulia Rizzoli, Francesco Barbato, Andrea Maracani, Marco Toldo, Umberto Michieli, Yi Niu, Pietro Zanuttigh
Catastrophic forgetting of previous knowledge is a critical issue in continual learning typically handled through various regularization strategies.
no code implementations • 16 Sep 2023 • Yuwen Yang, Chang Liu, Xun Cai, Suizhi Huang, Hongtao Lu, Yue Ding
Federated Learning (FL) has emerged as a promising approach to enable collaborative learning among multiple clients while preserving data privacy.
1 code implementation • ICCV 2023 • Pengxu Wei, Yujing Sun, Xingbei Guo, Chang Liu, Jie Chen, Xiangyang Ji, Liang Lin
Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios.
1 code implementation • 30 Aug 2023 • Shuting He, Henghui Ding, Chang Liu, Xudong Jiang
This dataset encompasses a range of expressions: those referring to multiple targets, expressions with no specific target, and the single-target expressions.
Generalized Referring Expression Comprehension Referring Expression +1
1 code implementation • 22 Aug 2023 • Chang Liu, Bo Wu
Yet, the application of LLMs to graph data remains under-explored.
1 code implementation • ICCV 2023 • Henghui Ding, Chang Liu, Shuting He, Xudong Jiang, Chen Change Loy
To investigate the feasibility of using motion expressions to ground and segment objects in videos, we propose a large-scale dataset called MeViS, which contains numerous motion expressions to indicate target objects in complex environments.
Ranked #2 on Referring Video Object Segmentation on MeViS
1 code implementation • 14 Jul 2023 • Jingna Qiu, Frauke Wilm, Mathias Öttl, Maja Schlereth, Chang Liu, Tobias Heimann, Marc Aubreville, Katharina Breininger
We find that the efficiency of this method highly depends on the choice of AL step size (i. e., the combination of region size and the number of selected regions per WSI), and a suboptimal AL step size can result in redundant annotation requests or inflated computation costs.
no code implementations • 11 Jul 2023 • Dongbo Wang, Chang Liu, Zhixiao Zhao, Si Shen, Liu Liu, Bin Li, Haotian Hu, Mengcheng Wu, Litao Lin, Xue Zhao, Xiyu Wang
In the context of the rapid development of large language models, we have meticulously trained and introduced the GujiBERT and GujiGPT language models, which are foundational models specifically designed for intelligent information processing of ancient texts.
1 code implementation • 29 Jun 2023 • Zhao Wang, Chang Liu, Shaoting Zhang, Qi Dou
Foundation models have exhibited remarkable success in various applications, such as disease diagnosis and text report generation.
no code implementations • 19 Jun 2023 • Zesen Cheng, Peng Jin, Hao Li, Kehan Li, Siheng Li, Xiangyang Ji, Chang Liu, Jie Chen
Bottom-up methods are mainly perturbed by Inferior Positive (IP) errors due to the lack of prior object information.
no code implementations • 8 Jun 2023 • Shuxin Zheng, Jiyan He, Chang Liu, Yu Shi, Ziheng Lu, Weitao Feng, Fusong Ju, Jiaxi Wang, Jianwei Zhu, Yaosen Min, He Zhang, Shidi Tang, Hongxia Hao, Peiran Jin, Chi Chen, Frank Noé, Haiguang Liu, Tie-Yan Liu
In this paper, we introduce a novel deep learning framework, called Distributional Graphormer (DiG), in an attempt to predict the equilibrium distribution of molecular systems.
2 code implementations • CVPR 2023 • Chang Liu, Henghui Ding, Xudong Jiang
Existing classic RES datasets and methods commonly support single-target expressions only, i. e., one expression refers to one target object.
Generalized Referring Expression Segmentation Referring Expression +1
1 code implementation • 1 Jun 2023 • Chang Liu, HaoNing Wu, Yujie Zhong, Xiaoyun Zhang, Yanfeng Wang, Weidi Xie
Generative models have recently exhibited exceptional capabilities in text-to-image generation, but still struggle to generate image sequences coherently.
1 code implementation • 1 Jun 2023 • Arnaud Deza, Chang Liu, Pashootan Vaezipoor, Elias B. Khalil
In this work, we propose a simple yet novel Constraint Programming approach to find non-commutative algorithms for fast matrix multiplication or provide proof of infeasibility otherwise.
1 code implementation • 1 Jun 2023 • Chang Liu, Shunxin Xu, Jialun Peng, Kaidong Zhang, Dong Liu
To address this problem, we propose a two-stage image inpainting method termed SketchRefiner.
1 code implementation • CVPR 2023 • Yu Wang, Pengchong Qiao, Chang Liu, Guoli Song, Xiawu Zheng, Jie Chen
We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field.
no code implementations • 28 May 2023 • Quzhe Huang, Yutong Hu, Shengqi Zhu, Yansong Feng, Chang Liu, Dongyan Zhao
After examining the relation definitions in various ETRE tasks, we observe that all relations can be interpreted using the start and end time points of events.
no code implementations • 24 May 2023 • Chang Liu, Henghui Ding, Yulun Zhang, Xudong Jiang
However, the generic attention mechanism in Transformer only uses the language input for attention weight calculation, which does not explicitly fuse language features in its output.
no code implementations • 22 May 2023 • Jinsong Chen, Chang Liu, Kaiyuan Gao, Gaichao Li, Kun He
Graph Transformers, emerging as a new architecture for graph representation learning, suffer from the quadratic complexity on the number of nodes when handling large graphs.
4 code implementations • 20 May 2023 • Peng Jin, Hao Li, Zesen Cheng, Jinfa Huang, Zhennan Wang, Li Yuan, Chang Liu, Jie Chen
In this paper, we propose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) to simulate the conceptualizing and reasoning process of human beings.
1 code implementation • 19 May 2023 • Chang Liu, Dong Liu
Specifically, we train a lightweight condition adapter to establish the correlation between external conditions and internal representations of diffusion models.
Ranked #1 on Conditional Text-to-Image Synthesis on COCO 2017 val
Conditional Image Generation Conditional Text-to-Image Synthesis
1 code implementation • 18 May 2023 • Yitong Li, Chang Liu, Jie Ma
Weakly supervised learning based on scribble annotations in target extraction of remote sensing images has drawn much interest due to scribbles' flexibility in denoting winding objects and low cost of manually labeling.
no code implementations • 17 May 2023 • Hao Li, Peng Jin, Zesen Cheng, Songyang Zhang, Kai Chen, Zhennan Wang, Chang Liu, Jie Chen
Video question answering aims at answering a question about the video content by reasoning the alignment semantics within them.
1 code implementation • 14 May 2023 • Xi Yang, Kejiang Chen, Weiming Zhang, Chang Liu, Yuang Qi, Jie Zhang, Han Fang, Nenghai Yu
To allow third-parties to autonomously inject watermarks into generated text, we develop a watermarking framework for black-box language model usage scenarios.
no code implementations • 12 May 2023 • Chang Liu
This paper studies the equilibrium behavior in contests with stochastic progress.
1 code implementation • 3 May 2023 • Chang Liu, Hiromasa Tamaki, Tomoyasu Yokoyama, Kensuke Wakasugi, Satoshi Yotsuhashi, Minoru Kusaba, Ryo Yoshida
Stable or metastable crystal structures of assembled atoms can be predicted by finding the global or local minima of the energy surface defined on the space of the atomic configurations.
1 code implementation • CVPR 2023 • Xiao Yang, Chang Liu, Longlong Xu, Yikai Wang, Yinpeng Dong, Ning Chen, Hang Su, Jun Zhu
The goal of this work is to develop a more reliable technique that can carry out an end-to-end evaluation of adversarial robustness for commercial systems.
no code implementations • 27 Mar 2023 • Xiaoyan Qian, Chang Liu, Xiaojuan Qi, Siew-Chong Tan, Edmund Lam, Ngai Wong
3D automatic annotation has received increased attention since manually annotating 3D point clouds is laborious.
1 code implementation • CVPR 2023 • Chang Liu, Weiming Zhang, Xiangru Lin, Wei zhang, Xiao Tan, Junyu Han, Xiaomao Li, Errui Ding, Jingdong Wang
It employs a "divide-and-conquer" strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity.
Ranked #1 on Semi-Supervised Object Detection on COCO 10% labeled data (detector metric)
2 code implementations • CVPR 2023 • Yitian Zhang, Yue Bai, Chang Liu, Huan Wang, Sheng Li, Yun Fu
To fix this issue, we propose a general framework, named Frame Flexible Network (FFN), which not only enables the model to be evaluated at different frames to adjust its computation, but also reduces the memory costs of storing multiple models significantly.
4 code implementations • CVPR 2023 • Peng Jin, Jinfa Huang, Pengfei Xiong, Shangxuan Tian, Chang Liu, Xiangyang Ji, Li Yuan, Jie Chen
Contrastive learning-based video-language representation learning approaches, e. g., CLIP, have achieved outstanding performance, which pursue semantic interaction upon pre-defined video-text pairs.
Ranked #8 on Video Question Answering on MSRVTT-QA
no code implementations • ICCV 2023 • Kehan Li, Yian Zhao, Zhennan Wang, Zesen Cheng, Peng Jin, Xiangyang Ji, Li Yuan, Chang Liu, Jie Chen
Interactive segmentation enables users to segment as needed by providing cues of objects, which introduces human-computer interaction for many fields, such as image editing and medical image analysis.
4 code implementations • ICCV 2023 • Peng Jin, Hao Li, Zesen Cheng, Kehan Li, Xiangyang Ji, Chang Liu, Li Yuan, Jie Chen
Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i. e., p(candidates|query).
Ranked #15 on Video Retrieval on MSVD
no code implementations • 13 Mar 2023 • Zesen Cheng, Kehan Li, Peng Jin, Xiangyang Ji, Li Yuan, Chang Liu, Jie Chen
An intuitive materialization of our paradigm is Parallel Vertex Diffusion (PVD) to directly set vertex coordinates as the generation target and use a diffusion model to train and infer.
no code implementations • 7 Mar 2023 • Chang Liu, Sandra Paterlini
Stock price prediction is a crucial element in financial trading as it allows traders to make informed decisions about buying, selling, and holding stocks.
2 code implementations • 2 Mar 2023 • Xu Ma, Yuqian Zhou, Huan Wang, Can Qin, Bin Sun, Chang Liu, Yun Fu
Context clusters (CoCs) view an image as a set of unorganized points and extract features via simplified clustering algorithm.
no code implementations • 28 Feb 2023 • Chang Liu, Rui Zhang, Xishan Zhang, Yifan Hao, Zidong Du, Xing Hu, Ling Li, Qi Guo
The energy-efficient works try to decrease the precision of multiplication or replace the multiplication with energy-efficient operations such as addition or bitwise shift, to reduce the energy consumption of FP32 multiplications.
no code implementations • 28 Feb 2023 • Chang Liu, Yinpeng Dong, Wenzhao Xiang, Xiao Yang, Hang Su, Jun Zhu, Yuefeng Chen, Yuan He, Hui Xue, Shibao Zheng
In our benchmark, we evaluate the robustness of 55 typical deep learning models on ImageNet with diverse architectures (e. g., CNNs, Transformers) and learning algorithms (e. g., normal supervised training, pre-training, adversarial training) under numerous adversarial attacks and out-of-distribution (OOD) datasets.
no code implementations • 28 Feb 2023 • Chang Liu, Wenzhao Xiang, Yuan He, Hui Xue, Shibao Zheng, Hang Su
To address this issue, we proposed a novel method of Augmenting data with Adversarial examples via a Wavelet module (AdvWavAug), an on-manifold adversarial data augmentation technique that is simple to implement.
no code implementations • 28 Feb 2023 • Yifan Yang, Chang Liu, Zheng Zhang
Online optimization has gained increasing interest due to its capability of tracking real-world streaming data.
1 code implementation • ICCV 2023 • Henghui Ding, Chang Liu, Shuting He, Xudong Jiang, Philip H. S. Torr, Song Bai
However, since the target objects in these existing datasets are usually relatively salient, dominant, and isolated, VOS under complex scenes has rarely been studied.
1 code implementation • ICCV 2023 • Bo Fang, Wenhao Wu, Chang Liu, Yu Zhou, Yuxin Song, Weiping Wang, Xiangbo Shu, Xiangyang Ji, Jingdong Wang
In the refined embedding space, we represent text-video pairs as probabilistic distributions where prototypes are sampled for matching evaluation.
no code implementations • ICCV 2023 • Hongliang He, Jun Wang, Pengxu Wei, Fan Xu, Xiangyang Ji, Chang Liu, Jie Chen
Experiments on three nuclear instance segmentation datasets justify the superiority of TopoSeg, which achieves state-of-the-art performance.
1 code implementation • ICCV 2023 • Runyi Yu, Zhennan Wang, Yinhuai Wang, Kehan Li, Chang Liu, Haoyi Duan, Xiangyang Ji, Jie Chen
A typical way to introduce position information is adding the absolute Position Embedding (PE) to patch embedding before entering VTs.
1 code implementation • 31 Dec 2022 • Xin Ma, Chang Liu, Chunyu Xie, Long Ye, Yafeng Deng, Xiangyang Ji
Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency.
no code implementations • 28 Dec 2022 • Chang Liu, Shuangyang Li, Weijie Yuan, Xuemeng Liu, Derrick Wing Kwan Ng
This paper investigates the orthogonal time frequency space (OTFS) transmission for enabling ultra-reliable low-latency communications (URLLC).
no code implementations • 20 Dec 2022 • Chang Liu, Chongyang Tao, Xiubo Geng, Tao Shen, Dongyan Zhao, Can Xu, Binxing Jiao, Daxin Jiang
Different from previous works that only rely on one positive and hard negatives as candidate passages, we create dark examples that all have moderate relevance to the query through mixing-up and masking in discrete space.
no code implementations • 16 Dec 2022 • Wei Sun, Chengao Liu, Linyan Zhang, Yu Li, Pengxu Wei, Chang Liu, Jialing Zou, Jianbin Jiao, Qixiang Ye
Optimizing a convolutional neural network (CNN) for camouflaged object detection (COD) tends to activate local discriminative regions while ignoring complete object extent, causing the partial activation issue which inevitably leads to missing or redundant regions of objects.
1 code implementation • 15 Dec 2022 • Bohao Li, Chang Liu, Mengnan Shi, Xiaozhong Chen, Xiangyang Ji, Qixiang Ye
Adapting object detectors learned with sufficient supervision to novel classes under low data regimes is charming yet challenging.
no code implementations • 14 Dec 2022 • Kun Tang, Xu Cao, Zhipeng Cao, Tong Zhou, Erlong Li, Ao Liu, Shengtao Zou, Chang Liu, Shuqi Mei, Elena Sizikova, Chao Zheng
THMA has been deployed by the Tencent Map team to provide services to downstream companies and users, serving over 1, 000 labeling workers and producing more than 30, 000 kilometers of HD map data per day at most.
no code implementations • 30 Nov 2022 • Chang Liu
We study a two-period moral hazard problem; there are two agents, with action sets that are unknown to the principal.
1 code implementation • 25 Nov 2022 • Qiran Zou, Yu Yang, Wing Yin Cheung, Chang Liu, Xiangyang Ji
Unsupervised foreground-background segmentation aims at extracting salient objects from cluttered backgrounds, where Generative Adversarial Network (GAN) approaches, especially layered GANs, show great promise.
no code implementations • 23 Nov 2022 • Chang Liu, Xuemeng Liu, Zhiqiang Wei, Derrick Wing Kwan Ng, Robert Schober
With the proposed predictive approach, we can avoid full-scale CSI estimation and facilitate low-dimensional CE for transmit beamforming design such that the signaling overhead is reduced by a scale of $\frac{1}{N}$, where $N$ is the number of IRS elements.
no code implementations • CVPR 2023 • Zesen Cheng, Pengchong Qiao, Kehan Li, Siheng Li, Pengxu Wei, Xiangyang Ji, Li Yuan, Chang Liu, Jie Chen
Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted.
Optical Character Recognition (OCR) Weakly supervised Semantic Segmentation +1
no code implementations • 19 Nov 2022 • Chang Liu, Yuwen Yang, Yue Ding, Hongtao Lu
While most existing message-passing graph neural networks (MPNNs) are permutation-invariant in graph-level representation learning and permutation-equivariant in node- and edge-level representation learning, their expressive power is commonly limited by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test.
no code implementations • 16 Nov 2022 • Xinyu Zhou, Chang Liu, Jun Zhao
The Metaverse has received much attention recently.
no code implementations • 15 Nov 2022 • Kun He, Chang Liu, Stephen Lin, John E. Hopcroft
And further combination with our feature augmentation techniques, termed LOMA_IF&FO, can continue to strengthen the model and outperform advanced intensity transformation methods for data augmentation.
1 code implementation • 6 Nov 2022 • Yu Yang, Xiaotian Cheng, Chang Liu, Hakan Bilen, Xiangyang Ji
In recent years, generative adversarial networks (GANs) have been an actively studied topic and shown to successfully produce high-quality realistic images in various domains.
no code implementations • 5 Nov 2022 • Yu Yang, Wing Yin Cheung, Chang Liu, Xiangyang Ji
Multiview self-supervised representation learning roots in exploring semantic consistency across data of complex intra-class variation.
no code implementations • 2 Nov 2022 • Yifei Zhang, Chang Liu, Yu Zhou, Weiping Wang, Qixiang Ye, Xiangyang Ji
In this paper, we present relation-aware contrastive self-supervised learning (ReCo) to integrate instance relations, i. e., global distribution relation and local interpolation relation, into the CSL framework in a plug-and-play fashion.
1 code implementation • 1 Nov 2022 • Chang Liu, Yuwen Yang, Zhe Xie, Hongtao Lu, Yue Ding
2) Prevailing graph augmentation methods for GEL, including rule-based, sample-based, adaptive, and automated methods, are not suitable for augmenting subgraphs because a subgraph contains fewer nodes but richer information such as position, neighbor, and structure.
no code implementations • 28 Oct 2022 • Ligen Shi, Chang Liu, Di He, Xing Zhao, Jun Qiu
A major challenge for matching-based depth estimation is to prevent mismatches in occlusion and smooth regions.
1 code implementation • 28 Oct 2022 • Henghui Ding, Chang Liu, Suchen Wang, Xudong Jiang
We propose a Vision-Language Transformer (VLT) framework for referring segmentation to facilitate deep interactions among multi-modal information and enhance the holistic understanding to vision-language features.
Ranked #3 on Referring Video Object Segmentation on MeViS
Referring Expression Segmentation Referring Video Object Segmentation
no code implementations • 28 Oct 2022 • Chang Liu, Yuwen Yang, Xun Cai, Yue Ding, Hongtao Lu
Federated learning (FL) faces three major difficulties: cross-domain, heterogeneous models, and non-i. i. d.
no code implementations • CVPR 2023 • Pengchong Qiao, Zhidan Wei, Yu Wang, Zhennan Wang, Guoli Song, Fan Xu, Xiangyang Ji, Chang Liu, Jie Chen
Semi-supervised learning (SSL) essentially pursues class boundary exploration with less dependence on human annotations.
no code implementations • 13 Oct 2022 • Chang Liu, Yuwen Yang, Yue Ding, Hongtao Lu
The normalizing layer has become one of the basic configurations of deep learning models, but it still suffers from computational inefficiency, interpretability difficulties, and low generality.
no code implementations • CVPR 2023 • Kehan Li, Zhennan Wang, Zesen Cheng, Runyi Yu, Yian Zhao, Guoli Song, Chang Liu, Li Yuan, Jie Chen
Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e. g., unsupervised semantic segmentation (USS).
1 code implementation • 9 Oct 2022 • Mingqing Xiao, Shuxin Zheng, Chang Liu, Zhouchen Lin, Tie-Yan Liu
To be specific, we develop invertible models to generate valid degraded images and meanwhile transform the distribution of lost contents to the fixed distribution of a latent variable during the forward degradation.
1 code implementation • Pattern Recognition and Computer Vision 2022 • Le Zhang, Qi Feng, Yao Lu, Chang Liu, and Guangming Lu
Attention mechanisms can effectively improve the performance of the mobile networks with a limited computational complexity cost.
no code implementations • 7 Oct 2022 • Chang Liu, Terence Jie Chua, Jun Zhao
Therefore, we formulate a joint learning and communication optimization problem to minimize total model parameter communication and computation delay, by optimizing local iteration counts and edge iteration counts.
no code implementations • 5 Oct 2022 • Wenhan Cao, Chang Liu, Zhiqian Lan, Shengbo Eben Li, Wei Pan, Angelo Alessandri
The accuracy of moving horizon estimation (MHE) suffers significantly in the presence of measurement outliers.
no code implementations • 26 Sep 2022 • Chang Liu, Xuemeng Liu, Shuangyang Li, Weijie Yuan, Derrick Wing Kwan Ng
Predictive beamforming design is an essential task in realizing high-mobility integrated sensing and communication (ISAC), which highly depends on the accuracy of the channel prediction (CP), i. e., predicting the angular parameters of users.
1 code implementation • 29 Aug 2022 • Chang Liu, Yujie Zhong, Andrew Zisserman, Weidi Xie
In this paper, we consider the problem of generalised visual object counting, with the goal of developing a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of "exemplars", i. e. zero-shot or few-shot counting.
Ranked #3 on Object Counting on CARPK
1 code implementation • 20 Jul 2022 • Chang Liu, Xiaoyan Qian, Binxiao Huang, Xiaojuan Qi, Edmund Lam, Siew-Chong Tan, Ngai Wong
By enriching the sparse point clouds, our method achieves 4. 48\% and 4. 03\% better 3D AP on KITTI moderate and hard samples, respectively, versus the state-of-the-art autolabeler.
no code implementations • 6 Jul 2022 • Zhennan Wang, Kehan Li, Runyi Yu, Yian Zhao, Pengchong Qiao, Chang Liu, Fan Xu, Xiangyang Ji, Guoli Song, Jie Chen
In this paper, we analyze batch normalization from the perspective of discriminability and find the disadvantages ignored by previous studies: the difference in $l_2$ norms of sample features can hinder batch normalization from obtaining more distinguished inter-class features and more compact intra-class features.
no code implementations • 4 Jul 2022 • Chang Liu, Yugong Luo, Pengfei Li, Chunhui Xing, Weiwei Kong
To deal with this problem, this paper introduces a two-dimensional maneuver management framework with a fault-tolerant mechanism on the basis of the proposed hierarchical architecture for the platoon control system.
1 code implementation • 4 Jul 2022 • Chang Liu, Gang Yang, Shuo Wang, Hangxu Wang, Yunhua Zhang, Yutao Wang
We employ the powerful feature extraction capability of Transformer (PVTv2) to extract global semantic information from RGB data and design a lightweight CNN backbone (LWDepthNet) to extract spatial structure information from depth data without pre-training.
no code implementations • 25 Jun 2022 • HongBing Zhang, Xinyi Liu, Chang Liu, HongTao Fan, YaJing Li, Xinyun Zhu
The proposed function is generalized to tensor cases, yielding tensor MLCP and weighted tensor $L\gamma$-norm.
1 code implementation • 9 Jun 2022 • Si Shen, Jiangfeng Liu, Litao Lin, Ying Huang, Lin Zhang, Chang Liu, Yutong Feng, Dongbo Wang
The academic literature of social sciences records human civilization and studies human social problems.
no code implementations • 2 Jun 2022 • Chang Liu, Zhen-Hua Ling, Ling-Hui Chen
This paper proposes a multilingual speech synthesis method which combines unsupervised phonetic representations (UPR) and supervised phonetic representations (SPR) to avoid reliance on the pronunciation dictionaries of target languages.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 25 May 2022 • Eduardo Pérez-Pellitero, Sibi Catley-Chandar, Richard Shaw, Aleš Leonardis, Radu Timofte, Zexin Zhang, Cen Liu, Yunbo Peng, Yue Lin, Gaocheng Yu, Jin Zhang, Zhe Ma, Hongbin Wang, Xiangyu Chen, Xintao Wang, Haiwei Wu, Lin Liu, Chao Dong, Jiantao Zhou, Qingsen Yan, Song Zhang, Weiye Chen, Yuhang Liu, Zhen Zhang, Yanning Zhang, Javen Qinfeng Shi, Dong Gong, Dan Zhu, Mengdi Sun, Guannan Chen, Yang Hu, Haowei Li, Baozhu Zou, Zhen Liu, Wenjie Lin, Ting Jiang, Chengzhi Jiang, Xinpeng Li, Mingyan Han, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Juan Marín-Vega, Michael Sloth, Peter Schneider-Kamp, Richard Röttger, Chunyang Li, Long Bao, Gang He, Ziyao Xu, Li Xu, Gen Zhan, Ming Sun, Xing Wen, Junlin Li, Shuang Feng, Fei Lei, Rui Liu, Junxiang Ruan, Tianhong Dai, Wei Li, Zhan Lu, Hengyan Liu, Peian Huang, Guangyu Ren, Yonglin Luo, Chang Liu, Qiang Tu, Fangya Li, Ruipeng Gang, Chenghua Li, Jinjing Li, Sai Ma, Chenming Liu, Yizhen Cao, Steven Tel, Barthelemy Heyrman, Dominique Ginhac, Chul Lee, Gahyeon Kim, Seonghyun Park, An Gia Vien, Truong Thanh Nhat Mai, Howoon Yoon, Tu Vo, Alexander Holston, Sheir Zaheer, Chan Y. Park
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
1 code implementation • 13 May 2022 • Xingchen Zhao, Chang Liu, Anthony Sicilia, Seong Jae Hwang, Yun Fu
Thus, it is still possible that those methods can overfit to source domains and perform poorly on target domains.
no code implementations • 28 Apr 2022 • Sijia Li, Gaopeng Gou, Chang Liu, Chengshang Hou, Zhenzhen Li, Gang Xiong
In this paper, we propose a Temporal Transaction Aggregation Graph Network (TTAGN) to enhance phishing scams detection performance on Ethereum.
no code implementations • 26 Apr 2022 • Chang Liu, Xudong Jiang, Henghui Ding
In this work, we propose a novel framework that simultaneously detects the target-of-interest via feature propagation and generates a fine-grained segmentation mask.
1 code implementation • 21 Apr 2022 • Tianyu Cui, Gaopeng Gou, Gang Xiong, Chang Liu, Peipei Fu, Zhen Li
6GAN forces multiple generators to train with a multi-class discriminator and an alias detector to generate non-aliased active targets with different addressing pattern types.
1 code implementation • 20 Apr 2022 • Tianyu Cui, Gaopeng Gou, Gang Xiong, Zhen Li, Mingxin Cui, Chang Liu
To do this, we propose an IPv6 address correlation model - SiamHAN.
1 code implementation • CVPR 2022 • Chang Liu, Chun Yang, Xu-Cheng Yin
Contextual information can be decomposed into temporal information and linguistic information.
no code implementations • 6 Apr 2022 • Wenhan Cao, Jingliang Duan, Shengbo Eben Li, Chen Chen, Chang Liu, Yu Wang
Both the primal and dual estimators are learned from data using supervised learning techniques, and the explicit sample size is provided, which enables us to guarantee the quality of each learned estimator in terms of feasibility and optimality.
no code implementations • 29 Mar 2022 • Chang Liu, Xiaoyan Qian, Xiaojuan Qi, Edmund Y. Lam, Siew-Chong Tan, Ngai Wong
While a few previous studies tried to automatically generate 3D bounding boxes from weak labels such as 2D boxes, the quality is sub-optimal compared to human annotators.
no code implementations • 10 Mar 2022 • Chang Liu, Chun Yang, Hai-Bo Qin, Xiaobin Zhu, Cheng-Lin Liu, Xu-Cheng Yin
Scene text recognition is a popular topic and extensively used in the industry.
3 code implementations • 9 Mar 2022 • Yu Shi, Shuxin Zheng, Guolin Ke, Yifei Shen, Jiacheng You, Jiyan He, Shengjie Luo, Chang Liu, Di He, Tie-Yan Liu
This technical note describes the recent updates of Graphormer, including architecture design modifications, and the adaption to 3D molecular dynamics simulation.
no code implementations • 6 Mar 2022 • Jiayi Zhang, Chang Liu, Junchi Yan, Xijun Li, Hui-Ling Zhen, Mingxuan Yuan
This paper surveys the trend of leveraging machine learning to solve mixed integer programming (MIP) problems.
no code implementations • 1 Mar 2022 • Qi Zhang, Chang Liu, Stephen Wu, Ryo Yoshida
The design variables consist of a set of reactants in a reaction network and its network topology.
no code implementations • 28 Feb 2022 • Yu Shi, Shuxin Zheng, Guolin Ke, Yifei Shen, Jiacheng You, Jiyan He, Shengjie Luo, Chang Liu, Di He, Tie-Yan Liu
This technical note describes the recent updates of Graphormer, including architecture design modifications, and the adaption to 3D molecular dynamics simulation.
no code implementations • 26 Feb 2022 • Vikram Shree, Carlos Diaz-Ruiz, Chang Liu, Bharath Hariharan, Mark Campbell
This paper focuses on the problem of decentralized pedestrian tracking using a sensor network.
no code implementations • 9 Feb 2022 • Jie Chen, Chang Liu, Jiawu Xie, Jie An, Nan Huang
In particular, this method breaks through the limitations of the existing methods, not only achieves good results in multivariate separation, but also effectively separates signals when mixed with 40dB Gaussian noise signals.
1 code implementation • 3 Feb 2022 • Jinhua Zhu, Yingce Xia, Chang Liu, Lijun Wu, Shufang Xie, Yusong Wang, Tong Wang, Tao Qin, Wengang Zhou, Houqiang Li, Haiguang Liu, Tie-Yan Liu
Molecular conformation generation aims to generate three-dimensional coordinates of all the atoms in a molecule and is an important task in bioinformatics and pharmacology.
1 code implementation • 26 Jan 2022 • Minoru Kusaba, Chang Liu, Ryo Yoshida
The prediction of energetically stable crystal structures formed by a given chemical composition is a central problem in solid-state physics.
no code implementations • 19 Jan 2022 • Zhongyuan Guo, Hong Zheng, Changhui You, Tianyu Wang, Chang Liu
We first analyze the production principle of anti-counterfeiting QR code, and convert the identification of copy forgery to device category forensics, and then a Dual-Branch Multi-Scale Feature Fusion network is proposed.
1 code implementation • NeurIPS 2021 • Xinwei Sun, Botong Wu, Xiangyu Zheng, Chang Liu, Wei Chen, Tao Qin, Tie-Yan Liu
To avoid such a spurious correlation, we propose \textbf{La}tent \textbf{C}ausal \textbf{I}nvariance \textbf{M}odels (LaCIM) that specifies the underlying causal structure of the data and the source of distributional shifts, guiding us to pursue only causal factor for prediction.
1 code implementation • 29 Nov 2021 • Mengnan Shi, Chang Liu, Qixiang Ye, Jianbin Jiao
Gating modules have been widely explored in dynamic network pruning to reduce the run-time computational cost of deep neural networks while preserving the representation of features.
no code implementations • 20 Nov 2021 • Long Gao, Chang Liu, Dooman Arefan, Ashok Panigrahy, Shandong Wu
These methods mainly focus on capturing either compact or descriptive features, where the information of the samples of a given one class is not sufficiently utilized.
no code implementations • 20 Nov 2021 • Long Gao, Chang Liu, Dooman Arefan, Ashok Panigrahy, Margarita L. Zuley, Shandong Wu
To address this challenge, we propose a medical-knowledge-guided one-class classification approach that leverages domain-specific knowledge of classification tasks to boost the model's performance.
1 code implementation • 16 Nov 2021 • Hengzhi Pei, Kan Ren, Yuqing Yang, Chang Liu, Tao Qin, Dongsheng Li
In this paper, we propose a novel generative framework for RTS data - RTSGAN to tackle the aforementioned challenges.
no code implementations • 1 Nov 2021 • Haoji Liu, Weichao Zhuang, Guodong Yin, Rongcan Li, Chang Liu, Shanxing Zhou
We first formulate the optimal merging control problem, which includes the constraints of safety and vehicle dynamics, with the objectives of minimizing travel time and energy consumption.
no code implementations • 1 Nov 2021 • Chang Liu, Chen Gao, Depeng Jin, Yong Li
We first conduct information propagation on two sub-graphs to learn the representations of POIs and users.
1 code implementation • NeurIPS 2021 • Jongjin Park, Younggyo Seo, Chang Liu, Li Zhao, Tao Qin, Jinwoo Shin, Tie-Yan Liu
Behavioral cloning has proven to be effective for learning sequential decision-making policies from expert demonstrations.
1 code implementation • 17 Oct 2021 • Yuefeng Chen, Xiaofeng Mao, Yuan He, Hui Xue, Chao Li, Yinpeng Dong, Qi-An Fu, Xiao Yang, Tianyu Pang, Hang Su, Jun Zhu, Fangcheng Liu, Chao Zhang, Hongyang Zhang, Yichi Zhang, Shilong Liu, Chang Liu, Wenzhao Xiang, Yajie Wang, Huipeng Zhou, Haoran Lyu, Yidan Xu, Zixuan Xu, Taoyu Zhu, Wenjun Li, Xianfeng Gao, Guoqiu Wang, Huanqian Yan, Ying Guo, Chaoning Zhang, Zheng Fang, Yang Wang, Bingyang Fu, Yunfei Zheng, Yekui Wang, Haorong Luo, Zhen Yang
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input.
no code implementations • 14 Oct 2021 • Chang Liu, Hairong Tang, Luyan Ji, Yongchao Zhao
Based on the mapping results, we analyzed the changes of Miyun Reservoir from 1984 to 2020 and the driving factors of them.
no code implementations • 11 Oct 2021 • Chang Liu
The principal knows the reward of the task and provides information to the agent over time in order to motivate effort.
no code implementations • 1 Oct 2021 • Chongyang Tao, Jiazhan Feng, Chang Liu, Juntao Li, Xiubo Geng, Daxin Jiang
For this task, the adoption of pre-trained language models (such as BERT) has led to remarkable progress in a number of benchmarks.
no code implementations • 30 Sep 2021 • Zijian Zhu, Hang Su, Chang Liu, Wenzhao Xiang, Shibao Zheng
Fortunately, most existing adversarial patches can be outwitted, disabled and rejected by a simple classification network called an adversarial patch detector, which distinguishes adversarial patches from original images.
no code implementations • CVPR 2022 • Chang Liu, Xiang Yu, Yi-Hsuan Tsai, Ramin Moslemi, Masoud Faraki, Manmohan Chandraker, Yun Fu
Convolutional Neural Networks have achieved remarkable success in face recognition, in part due to the abundant availability of data.
no code implementations • 29 Sep 2021 • Qiwei Ye, Yuxuan Song, Chang Liu, Fangyun Wei, Tao Qin, Tie-Yan Liu
Stochastic polic have been widely applied for their good property in exploration and uncertainty quantification.
Ranked #1 on MuJoCo Games on Ant-v3
no code implementations • 13 Sep 2021 • Wenzhao Xiang, Hang Su, Chang Liu, Yandong Guo, Shibao Zheng
As designers of artificial intelligence try to outwit hackers, both sides continue to hone in on AI's inherent vulnerabilities.
no code implementations • 26 Aug 2021 • Chang Liu, Weijie Yuan, Shuangyang Li, Xuemeng Liu, Husheng Li, Derrick Wing Kwan Ng, Yonghui Li
Specifically, the convolution and LSTM modules are successively adopted in the proposed HCL-Net to exploit the spatial and temporal dependencies of communication channels to further improve the learning performance.
no code implementations • ICML Workshop AML 2021 • Wenzhao Xiang, Chang Liu, Shibao Zheng
Traditional adversarial examples are typically generated by adding perturbation noise to the input image within a small matrix norm.
1 code implementation • ICCV 2021 • Henghui Ding, Chang Liu, Suchen Wang, Xudong Jiang
We introduce transformer and multi-head attention to build a network with an encoder-decoder attention mechanism architecture that "queries" the given image with the language expression.
no code implementations • 3 Aug 2021 • Chang Liu, Han Yu, Boyang Li, Zhiqi Shen, Zhanning Gao, Peiran Ren, Xuansong Xie, Lizhen Cui, Chunyan Miao
Noisy labels are commonly found in real-world data, which cause performance degradation of deep neural networks.
no code implementations • 16 Jul 2021 • Haodi Jiang, Ju Jing, Jiasheng Wang, Chang Liu, Qin Li, Yan Xu, Jason T. L. Wang, Haimin Wang
Our method consists of a data pre-processing component that prepares training data from a threshold-based tool, a deep learning model implemented as a Bayesian convolutional neural network for probabilistic image segmentation with uncertainty quantification to predict fibrils, and a post-processing component containing a fibril-fitting algorithm to determine fibril orientations.
1 code implementation • NeurIPS 2021 • Chang Liu, Haoyue Tang, Tao Qin, Jintao Wang, Tie-Yan Liu
This is motivated by the observation that deep generative models, in addition to a likelihood model $p(x|z)$, often also use an inference model $q(z|x)$ for extracting representation, but they rely on a usually uninformative prior distribution $p(z)$ to define a joint distribution, which may render problems like posterior collapse and manifold mismatch.
no code implementations • 25 Jun 2021 • Tianle Yue, Hang Yang, Zongliang Du, Chang Liu, Khalil I. Elkhodary, Shan Tang, Xu Guo
During offline training, a mapping function is built between high and low resolution representations of a given design domain.
no code implementations • 24 Jun 2021 • Xianlong Zeng, Simon Lin, Chang Liu
In addition, our framework showed a great generalizability potential to transfer learned knowledge from one institution to another, paving the way for future healthcare model pre-training across institutions.
1 code implementation • 24 Jun 2021 • Xianlong Zeng, Fanghao Song, Zhongen Li, Krerkkiat Chusap, Chang Liu
Our method can be divided into three stages: 1) a neighborhood generation stage, which generates instances based on the given sample; 2) a classification stage, which yields classifications on the generated instances to carve out the local decision boundary and delineate the model behavior; and 3) a human-in-the-loop stage, which involves human to refine and explore the neighborhood of interest.
BIG-bench Machine Learning Explainable artificial intelligence +1
no code implementations • 23 Jun 2021 • Xianlong Zeng, Simon Lin, Chang Liu
The claims data, containing medical codes, services information, and incurred expenditure, can be a good resource for estimating an individual's health condition and medical risk level.
2 code implementations • ICLR 2022 • Jiaxin Shi, Chang Liu, Lester Mackey
We introduce a new family of particle evolution samplers suitable for constrained domains and non-Euclidean geometries.
2 code implementations • CVPR 2021 • Zonghao Guo, Chang Liu, Xiaosong Zhang, Jianbin Jiao, Xiangyang Ji, Qixiang Ye
Detecting oriented and densely packed objects remains challenging for spatial feature aliasing caused by the intersection of reception fields between objects.
Ranked #34 on Object Detection In Aerial Images on DOTA (using extra training data)
no code implementations • 18 Jun 2021 • Chang Liu, Xiaolin Wu
Nighttime photographers are often troubled by light pollution of unwanted artificial lights.
1 code implementation • ICLR 2022 • Sang-gil Lee, Heeseung Kim, Chaehun Shin, Xu Tan, Chang Liu, Qi Meng, Tao Qin, Wei Chen, Sungroh Yoon, Tie-Yan Liu
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density.
no code implementations • 5 Jun 2021 • Jingjing Si, Guoliang Li, Yinbo Cheng, Rui Zhang, Godwin Enemali, Chang Liu
As an in situ combustion diagnostic tool, Tunable Diode Laser Absorption Spectroscopy (TDLAS) tomography has been widely used for imaging of two-dimensional temperature distributions in reactive flows.
no code implementations • 18 May 2021 • Chang Liu, Guanjie Zheng, Zhenhui Li
Therefore, in this paper, we propose to learn the human routing model, which is one of the most essential part in the traffic simulator.
no code implementations • 26 Apr 2021 • Jie Chen, Jie Liu, Chang Liu, Jian Zhang, Bing Han
To overcome this issue and to further improve the recognition performance, we adopt a deep learning approach for underwater target recognition and propose a LOFAR spectrum enhancement (LSE)-based underwater target recognition scheme, which consists of preprocessing, offline training, and online testing.
1 code implementation • ICCV 2021 • Kai Li, Chang Liu, Handong Zhao, Yulun Zhang, Yun Fu
This paper studies Semi-Supervised Domain Adaptation (SSDA), a practical yet under-investigated research topic that aims to learn a model of good performance using unlabeled samples and a few labeled samples in the target domain, with the help of labeled samples from a source domain.
no code implementations • 6 Apr 2021 • Boyu Yang, Mingbao Lin, Binghao Liu, Mengying Fu, Chang Liu, Rongrong Ji, Qixiang Ye
By tentatively expanding network nodes, LEC-Net enlarges the representation capacity of features, alleviating feature drift of old network from the perspective of model regularization.
1 code implementation • CVPR 2021 • Chang Liu, Han Yu, Boyang Li, Zhiqi Shen, Zhanning Gao, Peiran Ren, Xuansong Xie, Lizhen Cui, Chunyan Miao
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models.
no code implementations • 22 Mar 2021 • Hua Wei, Chacha Chen, Chang Liu, Guanjie Zheng, Zhenhui Li
Simulation of the real-world traffic can be used to help validate the transportation policies.
no code implementations • 22 Mar 2021 • Chang Liu, Xiaojuan Qi, Edmund Lam, Ngai Wong
The neuromorphic event cameras, which capture the optical changes of a scene, have drawn increasing attention due to their high speed and low power consumption.
no code implementations • 17 Mar 2021 • Juntao Li, Chang Liu, Chongyang Tao, Zhangming Chan, Dongyan Zhao, Min Zhang, Rui Yan
To fill the gap between these up-to-date methods and the real-world applications, we incorporate user-specific dialogue history into the response selection and propose a personalized hybrid matching network (PHMN).
no code implementations • 16 Mar 2021 • Chang Liu, Lixin Fan, Kam Woh Ng, Yilun Jin, Ce Ju, Tianyu Zhang, Chee Seng Chan, Qiang Yang
This paper proposes a novel ternary hash encoding for learning to hash methods, which provides a principled more efficient coding scheme with performances better than those of the state-of-the-art binary hashing counterparts.
2 code implementations • CVPR 2021 • Bohao Li, Boyu Yang, Chang Liu, Feng Liu, Rongrong Ji, Qixiang Ye
Few-shot object detection has made substantial progressby representing novel class objects using the feature representation learned upon a set of base class objects.
Ranked #14 on Few-Shot Object Detection on MS-COCO (10-shot)
no code implementations • 6 Mar 2021 • Jeremy Beauchamp, Razvan Bunescu, Cindy Marling, Zhongen Li, Chang Liu
In this work, we invert the "what-if" scenario and introduce a similar architecture based on chaining two LSTMs that can be trained to make either insulin or carbohydrate recommendations aimed at reaching a desired BG level in the future.
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 • 3 Mar 2021 • Jindong Wang, Wenjie Feng, Chang Liu, Chaohui Yu, Mingxuan Du, Renjun Xu, Tao Qin, Tie-Yan Liu
Being expensive and time-consuming to collect massive COVID-19 image samples to train deep classification models, transfer learning is a promising approach by transferring knowledge from the abundant typical pneumonia datasets for COVID-19 image classification.
1 code implementation • 2 Mar 2021 • Jindong Wang, Cuiling Lan, Chang Liu, Yidong Ouyang, Tao Qin, Wang Lu, Yiqiang Chen, Wenjun Zeng, Philip S. Yu
Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain.
no code implementations • 10 Feb 2021 • Rui Zhang, Jingjing Si, Godwin Enemali, Yong Bao, Chang Liu
The proposed scheme was both numerically and experimentally validated using a CST sensor with 32 laser beams using a variety of computational tomographic algorithms.
no code implementations • 22 Jan 2021 • Chang Liu, Henghui Ding, Xudong Jiang
In this paper, we argue that recovering these microscopic details relies on low-level but high-definition texture features.
no code implementations • 20 Jan 2021 • Zhuqing Jiang, Chang Liu, Ya'nan Wang, Kai Li, Aidong Men, Haiying Wang, Haiyong Luo
With the goal of tuning up the brightness, low-light image enhancement enjoys numerous applications, such as surveillance, remote sensing and computational photography.
no code implementations • 6 Jan 2021 • Bernhard Kliem, Jeongwoo Lee, Rui Liu, Stephen M. White, Chang Liu, Satoshi Masuda
We present evidence that a magnetic flux rope was formed before a coronal mass ejection (CME) and its associated long-duration flare during a pair of preceding confined eruptions and associated impulsive flares in a compound event in NOAA Active Region 12371.
Solar and Stellar Astrophysics
no code implementations • 4 Jan 2021 • Ya'nan Wang, Zhuqing Jiang, Chang Liu, Kai Li, Aidong Men, Haiying Wang
This paper proposes a neural network for multi-level low-light image enhancement, which is user-friendly to meet various requirements by selecting different images as brightness reference.
no code implementations • 1 Jan 2021 • Chang Liu, Kai Li, Yun Fu
Unsupervised domain adaptation (UDA) is to make predictions for unlabeled data in a target domain with labeled data from source domain available.
2 code implementations • 16 Dec 2020 • Chang Liu, Zetian Jiang, Runzhong Wang, Junchi Yan, Lingxiao Huang, Pinyan Lu
As such, the agent can finish inlier matching timely when the affinity score stops growing, for which otherwise an additional parameter i. e. the number of inliers is needed to avoid matching outliers.
no code implementations • 7 Dec 2020 • Chang Liu, Yixing Huang, Joscha Maier, Laura Klein, Marc Kachelrieß, Andreas Maier
For organ-specific AEC, a preliminary CT reconstruction is necessary to estimate organ shapes for dose optimization, where only a few projections are allowed for real-time reconstruction.