Cross-domain Named Entity Recognition (NER) transfers the NER knowledge from high-resource domains to the low-resource target domain.
Inspired by Bayesian hierarchical models, we develop ActPerFL, a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients’ training.
1 code implementation • 19 Sep 2023 • Aiyuan Yang, Bin Xiao, Bingning Wang, Borong Zhang, Ce Bian, Chao Yin, Chenxu Lv, Da Pan, Dian Wang, Dong Yan, Fan Yang, Fei Deng, Feng Wang, Feng Liu, Guangwei Ai, Guosheng Dong, Haizhou Zhao, Hang Xu, Haoze Sun, Hongda Zhang, Hui Liu, Jiaming Ji, Jian Xie, Juntao Dai, Kun Fang, Lei Su, Liang Song, Lifeng Liu, Liyun Ru, Luyao Ma, Mang Wang, Mickel Liu, MingAn Lin, Nuolan Nie, Peidong Guo, Ruiyang Sun, Tao Zhang, Tianpeng Li, Tianyu Li, Wei Cheng, WeiPeng Chen, Xiangrong Zeng, Xiaochuan Wang, Xiaoxi Chen, Xin Men, Xin Yu, Xuehai Pan, Yanjun Shen, Yiding Wang, Yiyu Li, Youxin Jiang, Yuchen Gao, Yupeng Zhang, Zenan Zhou, Zhiying Wu
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving.
However, the performance of the proposed CNN model varies: for evaluation tasks that are consistent with the trained network type, the proposed CNN model consistently achieves accurate evaluations of both attack curves and robustness values across all removal scenarios.
In this way, computational complexity of this method is greatly reduced compared to that of traditional pixel-based extraction methods, thus enabling large-scale pore-network extraction.
Association techniques mainly depend on the combination of motion and appearance information.
no code implementations • 17 Jul 2023 • Liangyu Zha, Junlin Zhou, Liyao Li, Rui Wang, Qingyi Huang, Saisai Yang, Jing Yuan, Changbao Su, Xiang Li, Aofeng Su, Tao Zhang, Chen Zhou, Kaizhe Shou, Miao Wang, Wufang Zhu, Guoshan Lu, Chao Ye, Yali Ye, Wentao Ye, Yiming Zhang, Xinglong Deng, Jie Xu, Haobo Wang, Gang Chen, Junbo Zhao
Tables are prevalent in real-world databases, requiring significant time and effort for humans to analyze and manipulate.
Emotion recognition is an important research direction in artificial intelligence, helping machines understand and adapt to human emotional states.
Particularly, we propose unsupervised alignment objectives to capture (1) local one-to-one alignment between the two different modalities, (2) alignment via multi-modality contexts to leverage information from additional modalities, and (3) alignment via multilingual contexts where additional bilingual dictionaries are incorporated.
The proposed model, which combines the graph neural network and the pointer mechanism, can effectively map from the solver state to the branching variable decisions.
Motivated by this, we propose a positive-augmentation and positive-mixup positive-unlabeled metric learning framework (P3M).
In this report, we successfully validated the effectiveness of the decoupling strategy in video panoptic segmentation.
However, recent work in 2D has hinted that there may be differences between the two models in systems with heterotypic interfaces between two tissue types, and there is a burgeoning interest in 3D tissue models.
The efficacy of the decoupling strategy relies on two crucial elements: 1) attaining precise long-term alignment outcomes via frame-by-frame association during tracking, and 2) the effective utilization of temporal information predicated on the aforementioned accurate alignment outcomes during refinement.
Ranked #1 on Video Panoptic Segmentation on VIPSeg
Prototype is widely used to represent internal structure of category for few-shot learning, which was proposed as a simple inductive bias to address the issue of overfitting.
Keyword Spotting (KWS) is a critical aspect of audio-based applications on mobile devices and virtual assistants.
We postulate that the enhancement of ZEB2 expression driving this intermediate state is potentially due to chromatin reorganization.
Symmetric bi-manual manipulation is essential for various on-orbit operations due to its potent load capacity.
Extensive experiments are carried out to demonstrate that the images crafted by AdvRD are visually and statistically close to the natural raindrop images, can work as strong attackers to DNN models, and also help improve the robustness of DNNs to raindrop attacks.
In the early stage, our method loosens the practical constraints of unsafe transitions (adding extra safety budget) with the aid of a new metric we propose.
In space-time adaptive processing (STAP) of the airborne radar system, it is very important to realize sparse restoration of the clutter covariance matrix with a small number of samples.
The key idea is to reduce the number of parameters that rely on interview dialogs by disentangling the knowledge selector and dialog generator so that most parameters can be trained with ungrounded dialogs as well as the resume data that are not low-resource.
In contrast to the control-theoretic methods, the lack of stability guarantee remains a significant problem for model-free reinforcement learning (RL) methods.
To address the above two issues, in this study, a novel coevolutionary framework termed CoMMEA for multimodal multi-objective optimization is proposed to better obtain both global and local PSs, and simultaneously, to improve the convergence performance in dealing with high-dimension MMOPs.
Deep learning based methods have significantly boosted the study of automatic building extraction from remote sensing images.
To solve the common incomplete labeling problem, we propose a unified positive-unlabeled learning framework - shift and squared ranking loss positive-unlabeled (SSR-PU) learning.
Federated Learning (FL) has emerged as a means of distributed learning using local data stored at clients with a coordinating server.
To our best knowledge, the performance of the Spiking SiamFC++ outperforms the existing state-of-the-art approaches in SNN-based object tracking, which provides a novel path for SNN application in the field of target tracking.
To model the two-way selection preference from the dual-perspective of job seekers and employers, we incorporate two different nodes for each candidate (or job) and characterize both successful matching and failed matching via a unified dual-perspective interaction graph.
Therefore, this paper proposes a patient-specific game-based transfer (PSGT) method for PD severity prediction.
In this paper, we propose a framework of spectral filtering (shrinkage) for measuring the difference between query samples and prototypes, or namely the relative prototypes, in a reproducing kernel Hilbert space (RKHS).
Binary matrix optimization commonly arise in the real world, e. g., multi-microgrid network structure design problem (MGNSDP), which is to minimize the total length of the power supply line under certain constraints.
Multimodal multi-objective problems (MMOPs) commonly arise in real-world problems where distant solutions in decision space correspond to very similar objective values.
Module I realizes the multi-target trajectory planning for two end-effectors within a large target space.
We review current solutions and technical challenges for automatic speech recognition, keyword spotting, device arbitration, speech enhancement, and source localization in multidevice home environments to provide context for the INTERSPEECH 2022 special session, "Challenges and opportunities for signal processing and machine learning for multiple smart devices".
Therefore, guaranteeing the robustness of hard examples is crucial for improving the final robustness of the model.
Multi-objective orienteering problems (MO-OPs) are classical multi-objective routing problems and have received a lot of attention in the past decades.
In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background.
A dynamic pointer network (DYPN) is introduced as the TSP solver, which takes city locations as inputs and immediately outputs a permutation of nodes.
The model is trained using a deep reinforcement learning method offline, and is used to optimize the UAV routing problem online.
In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned.
As the core technique of online recruitment platforms, person-job fit can improve hiring efficiency by accurately matching job positions with qualified candidates.
In this paper, we propose a free-moving hypothesis plane method for dynamic and non-uniform sampling in a wide depth range to build the cost volume, which not only greatly reduces the number of planes but also finers sampling, for both of reducing computational cost and improving accuracy, named Non-Uniform Cost Volume.
In this paper, we introduce a novel contour-based method, named E2EC, for high-quality instance segmentation.
Ranked #95 on Instance Segmentation on COCO test-dev
Known solutions include the enhancement of training data and the increase of rotation invariance by globally merging the rotation equivariant features.
Federated learning (FL) has been developed as a promising framework to leverage the resources of edge devices, enhance customers' privacy, comply with regulations, and reduce development costs.
This paper presents a novel framework and a distributed algorithm that can enable ANs and CNs to autonomously "cooperate" with each other to dynamically negotiate their local QoS budgets and to collectively meet E2E QoS goals by sharing only their estimates of the global constraint functions, without disclosing their local decision variables.
Further, we propose Scale-Invariant (SI) adversarial defense mechanism based on the cosine angle matrix, which can be embedded into the popular adversarial defenses.
A revelation-principle-like design regime is established to show that the persuasion with belief hierarchies can be fully characterized by correlating the randomization of the agents' local BPD mechanisms with the persuasion as a direct recommendation of the future promises.
However, the defense methods that have good effect in natural images may not be suitable for medical diagnostic tasks.
Then, we transfer the pre-trained graph encoder to initialize the node embeddings on the target domain, which benefits the fine-tuning of the single domain recommender system on the target domain.
In this paper, we propose FedProc: prototypical contrastive federated learning, which is a simple and effective federated learning framework.
Virtual 3D try-on can provide an intuitive and realistic view for online shopping and has a huge potential commercial value.
no code implementations • 7 May 2021 • Jinjin Gu, Haoming Cai, Chao Dong, Jimmy S. Ren, Yu Qiao, Shuhang Gu, Radu Timofte, Manri Cheon, SungJun Yoon, Byungyeon Kang, Junwoo Lee, Qing Zhang, Haiyang Guo, Yi Bin, Yuqing Hou, Hengliang Luo, Jingyu Guo, ZiRui Wang, Hai Wang, Wenming Yang, Qingyan Bai, Shuwei Shi, Weihao Xia, Mingdeng Cao, Jiahao Wang, Yifan Chen, Yujiu Yang, Yang Li, Tao Zhang, Longtao Feng, Yiting Liao, Junlin Li, William Thong, Jose Costa Pereira, Ales Leonardis, Steven McDonagh, Kele Xu, Lehan Yang, Hengxing Cai, Pengfei Sun, Seyed Mehdi Ayyoubzadeh, Ali Royat, Sid Ahmed Fezza, Dounia Hammou, Wassim Hamidouche, Sewoong Ahn, Gwangjin Yoon, Koki Tsubota, Hiroaki Akutsu, Kiyoharu Aizawa
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021.
We propose a direct information design approach that incentivizes each agent to select the signal sent by the principal, such that the design process avoids the predictions of the agents' strategic selection behaviors.
This paper aims to verify the existence of aliasing in TAL methods and investigate utilizing low pass filters to solve this problem by inhibiting the high-frequency band.
Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images.
An obedient principle is established which states that it is without loss of generality to focus on the direct information design when the information design incentivizes each agent to select the signal sent by the designer, such that the design process avoids the predictions of the agents' strategic selection behaviors.
This paper introduces a new deep learning approach to approximately solve the Covering Salesman Problem (CSP).
On the other hand, we propose an accurate HSI noise model which matches the distribution of real data well and can be employed to synthesize realistic dataset.
More specifically, we first do partial visual and tactile features extraction from the partial visual and tactile data, respectively, and encode the extracted features in modality-specific feature subspaces.
A range of defense methods have been proposed to improve the robustness of neural networks on adversarial examples, among which provable defense methods have been demonstrated to be effective to train neural networks that are certifiably robust to the attacker.
Since the WW model is trained with the AFE-processed audio data, its performance is sensitive to AFE variations, such as gain changes.
This paper contributes to the treatment of extensive constraints in evolutionary many-constraint optimization through consideration of the relationships between pair-wise constraints.
In this way, the impact of data correlation is relieved with the proposed feature selection scheme, and moreover, the privacy issue of data correlation in learning is guaranteed.
A set of experiments on real-world and synthetic datasets show that our method is able to use unlabeled data to achieve a better trade-off between accuracy and discrimination.
Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data.
Extensive experiments show that our method is able to achieve fair semi-supervised learning, and reach a better trade-off between accuracy and fairness than fair supervised learning.
We propose a fast PnP solution named R1PPnP to handle outliers by utilizing a soft re-weighting mechanism and the 1-point RANSAC scheme.
Aiming at channel compression, a novel convolutional construction named compact convolution is proposed to embrace the progress in spatial convolution, channel grouping and pooling operation.
Online metric learning has been widely exploited for large-scale data classification due to the low computational cost.
Specifically, we propose to estimate the conditional mode by minimizing the derivative of the estimated conditional quantile function defined by smoothing the linear quantile regression estimator, and develop two bootstrap methods, a novel pivotal bootstrap and the nonparametric bootstrap, for our conditional mode estimator.
Statistics Theory Methodology Statistics Theory
The experiment of trajectory estimation demonstrates the convergence of AdaTE, and the better robust to the biased prior statistics and the observation drift compared with EKF, UKF and sparse MAP.
Information Theory Robotics Systems and Control Systems and Control Information Theory G.3.13; J.2.7
To effectively benefit both visual and tactile modalities for object clustering, in this paper, we propose a deep Auto-Encoder-like Non-negative Matrix Factorization framework for visual-tactile fusion clustering.
As a further optimization, we propose a density-adaptive regular-block (DARB) pruning that outperforms prior structured pruning work with high pruning ratio and decoding efficiency.
Furthermore, we extend the match network and implement domain adaptation in three levels, sentence-level representation, sentence-level match, and global match.
To solve the low spatial and/or temporal resolution problem which the conventional hypelrspectral cameras often suffer from, coded snapshot hyperspectral imaging systems have attracted more attention recently.
Recently, a few methods take relation paths into consideration but pay less attention to the order of relations in paths which is important for reasoning.
Ranked #3 on Link Prediction on FB15k (MR metric)
The model is trained jointly in a multi-task learning setting.
Most current image super-resolution (SR) methods based on convolutional neural networks (CNNs) use residual learning in network structural design, which favors to effective back propagation and hence improves SR performance by increasing model scale.
In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks.
As an important component in SON, self-healing is defined as a network paradigm where the faults of target networks are mitigated or recovered by automatically triggering a series of actions such as detection, diagnosis and compensation.
The solutions can be directly obtained by a simple forward calculation of the neural network; thereby, no iteration is required and the MOP can be always solved in a reasonable time.
The task-specific classifiers are required to be homogeneous-structured to ease the parameter prediction, so the meta-learning approaches could only handle few-shot learning problems where the tasks share a uniform number of classes.
Imbalanced data commonly exists in real world, espacially in sentiment-related corpus, making it difficult to train a classifier to distinguish latent sentiment in text data.
Generative Adversarial Networks (GANs) are powerful tools for reconstructing Compressed Sensing Magnetic Resonance Imaging (CS-MRI).
Phase equilibrium calculation, also known as flash calculation, has been extensively applied in petroleum engineering, not only as a standalone application for separation process but also an integral component of compositional reservoir simulation.
Single image super-resolution (SISR), especially that based on deep learning techniques, is an effective and promising alternative technique to improve the current spatial resolution of magnetic resonance (MR) images.
The proposed CSN model divides the hierarchical features into two branches, i. e., residual branch and dense branch, with different information transmissions.
Ranked #3 on Image Super-Resolution on IXI
Processing sequential data with long term dependencies and learn complex transitions are two major challenges in many deep learning applications.
Hyperspectral image (HSI) recovery from a single RGB image has attracted much attention, whose performance has recently been shown to be sensitive to the camera spectral sensitivity (CSS).
To overcome this problem, in this paper, an intra prediction convolutional neural network (IPCNN) is proposed for intra prediction, which exploits the rich context of the current block and therefore is capable of improving the accuracy of predicting the current block.
Weakly supervised temporal action detection is a Herculean task in understanding untrimmed videos, since no supervisory signal except the video-level category label is available on training data.
Methods of parameter pruning and quantization are described first, after that the other techniques are introduced.
no code implementations • 25 Jul 2017 • Changbo Fu, Xiaopeng Zhou, Xun Chen, Yunhua Chen, Xiangyi Cui, Deqing Fang, Karl Giboni, Franco Giuliani, Ke Han, Xingtao Huang, Xiangdong Ji, Yonglin Ju, Siao Lei, Shaoli Li, Huaxuan Liu, Jianglai Liu, Yugang Ma, Yajun Mao, Xiangxiang Ren, Andi Tan, Hongwei Wang, Jimin Wang, Meng Wang, Qiuhong Wang, Siguang Wang, Xuming Wang, Zhou Wang, Shiyong Wu, Mengjiao Xiao, Pengwei Xie, Binbin Yan, Yong Yang, Jianfeng Yue, Hongguang Zhang, Tao Zhang, Li Zhao, Ning Zhou
We report new searches for the solar axions and galactic axion-like dark matter particles, using the first low-background data from PandaX-II experiment at China Jinping Underground Laboratory, corresponding to a total exposure of about $2. 7\times 10^4$ kg$\cdot$day.
High Energy Physics - Experiment Solar and Stellar Astrophysics High Energy Physics - Phenomenology
Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.
Recently significant performance improvement in face detection was made possible by deeply trained convolutional networks.
In this paper we investigate user learning in authoritative technology adoption by developing an agent-based model using the case of council-led smart meter deployment in the UK City of Leeds.
In this paper, we develop an agent-based model which integrates four important elements, i. e. organisational energy management policies/regulations, energy management technologies, electric appliances and equipment, and human behaviour, based on a case study, to simulate the energy consumption in office buildings.
Privacy-preserving distributed machine learning becomes increasingly important due to the recent rapid growth of data.
In this paper, we develop an agent-based model which integrates four important elements, i. e. organisational energy management policies/regulations, energy management technologies, electric appliances and equipment, and human behaviour, to simulate the electricity consumption in office buildings.