检索结果-内蒙古大学图书馆

SAMREFINER: TAMING SEGMENT ANYTHING MODEL FOR UNIVERSAL MASK REFINEMENT

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lin, Yuqi Li, Hengjia Shao, Wenqi Yang, Zheng Zhao, Jun He, Xiaofei Luo, Ping Zhang, Kaipeng State Key Lab of CAD&CG College of Computer Science Zhejiang University China Shanghai AI Laboratory China FABU Inc The University of Hong Kong Hong Kong

In this paper, we explore a principal way to enhance the quality of widely preexisting coarse masks, enabling them to serve as reliable training data for segmentation models to reduce the annotation cost. In contrast to prior refinement techniques that are tailored to specific models or tasks in a close-world manner, we propose SAMRefiner, a universal and efficient approach by adapting SAM to the mask refinement task. The core technique of our model is the noise-tolerant prompting scheme. Specifically, we introduce a multi-prompt excavation strategy to mine diverse input prompts for SAM (i.e, distance-guided points, context-aware elastic bounding boxes, and Gaussian-style masks) from initial coarse masks. These prompts can collaborate with each other to mitigate the effect of defects in coarse masks. In particular, considering the difficulty of SAM to handle the multi-object case in semantic segmentation, we introduce a split-then-merge (STM) pipeline. Additionally, we extend our method to SAMRefiner++ by introducing an additional IoU adaption step to further boost the performance of the generic SAMRefiner on the target dataset. This step is self-boosted and requires no additional annotation. The proposed framework is versatile and can flexibly cooperate with existing segmentation methods. We evaluate our mask framework on a wide range of benchmarks under different settings, demonstrating better accuracy and efficiency. SAMRefiner holds significant potential to expedite the evolution of refinement tools. Our code is available at SAMRefiner. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

Prototype-based classifier learning for long-tailed visual recognition

学校读者我要写书评

暂无评论

science China(Information sciences) 2022年第6期65卷 62-76页

作者： Xiu-Shen WEI Shu-Lin XU Hao CHEN Liang XIAO Yuxin PENG School of Computer Science and Engineering Nanjing University of Science and Technology State Key Laboratory of Integrated Services Networks Xidian University Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security Wangxuan Institute of Computer Technology Peking University

In this paper, we tackle the long-tailed visual recognition problem from the categorical prototype perspective by proposing a prototype-based classifier learning(PCL) method. Specifically, thanks to the generalization ability and robustness, categorical prototypes reveal their advantages of representing the category semantics. Coupled with their class-balance characteristic, categorical prototypes also show potential for handling data imbalance. In our PCL, we propose to generate the categorical classifiers based on the prototypes by performing a learnable mapping function. To further alleviate the impact of imbalance on classifier generation, two kinds of classifier calibration approaches are designed from both prototype-level and example-level aspects. Extensive experiments on five benchmark datasets, including the large-scale iNaturalist, Places-LT,and ImageNet-LT, justify that the proposed PCL can outperform state-of-the-arts. Furthermore, validation experiments can demonstrate the effectiveness of tailored designs in PCL for long-tailed problems.

关键词： long-tailed distribution categorical prototype classifier generation classifier calibration class imbalance

Few-Shot Domain Adaptation for Charge Prediction on Unprofessional Descriptions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Jie Guan, Ziyu Zhao, Wei Jiang, Yue He, Xiaofei State Key Laboratory of Integrated Services Networks School of Computer Science and Technology Xidian University Shaanxi Xi’an710071 China State Key Lab of CAD&CG College of Computer Science Zhejiang University Zhejiang Hangzhou310058 China

—Recent works considering professional legal-linguistic style (PLLS) texts have shown promising results on the charge prediction task. However, unprofessional users also show an increasing demand on such a prediction service. There is a clear domain discrepancy between PLLS texts and non-PLLS texts expressed by those laypersons, which degrades the current SOTA models’ performance on non-PLLS texts. A key challenge is the scarcity of non-PLLS data for most charge classes. This paper proposes a novel few-shot domain adaptation (FSDA) method named Disentangled Legal Content for Charge Prediction (DLCCP). Compared with existing FSDA works, which solely perform instance-level alignment without considering the negative impact of text style information existing in latent features, DLCCP (1) disentangles the content and style representations for better domain-invariant legal content learning with carefully designed optimization goals for content and style spaces and, (2) employs the constitutive elements knowledge of charges to extract and align element-level and instance-level content representations simultaneously. We contribute the first publicly available non-PLLS dataset named NCCP for developing layperson-friendly charge prediction models. Experiments on NCCP show the superiority of our methods over competitive baselines. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

Topic Embedded Representation Enhanced Variational Wasserstein Autoencoder for Text Modeling 5

学校读者我要写书评

暂无评论

Topic Embedded Representation Enhanced Variational Wasserste...

5th IEEE International Conference on Electronics Technology, ICET 2022

作者： Xiang, Zheng Liu, Xiaoming Yang, Guan Liu, Yang Zhongyuan University of Technology School of Computer Science Zhengzhou China Henan Key Laboratory on Public Opinion Intelligent Analysis Zhengzhou China Key Laboratory of text processing and image understanding Zhengzhou China Xidian University State Key Laboratory of Integrated Services Networks Xi'an China Shandong University Key Lab of Cryptologic Technology and Information Security Ministry of Education Xi'an China

ISBN: (纸本)9781665485081

Variational Autoencoder (VAE) is now popular in modeling and language generation tasks, which need to pay attention to the diversity of generation results. The existing models are insufficient in capturing the built-in relationships between topic representation and sequential words. At the same time, there is a massive contradiction between the commonly used simple Gaussian prior and the actual complex distribution of languages. To address the above problems, we introduce a hybrid Wasserstein Autoencoder (WAE) with Topic Embedded Representation (TER) for modeling. TER is obtained through an embedding-based topic model and can capture the dependencies and semantic similarities between topics and words. In this case, the learned latent variable has rich semantic knowledge with the help of TER and is easier to explain and control. Our experiments show that our method is competitive with other VAEs in modeling. © 2022 IEEE.

关键词： Semantics

Preference detection of the humanoid robot face based on EEG and eye movement

学校读者我要写书评

暂无评论

Neural Computing and Applications 2024年第19期36卷 11603-11621页

作者： Wang, Pengchao Mu, Wei Zhan, Gege Wang, Aiping Song, Zuoting Fang, Tao Zhang, Xueze Wang, Junkongshuai Niu, Lan Bin, Jianxiong Zhang, Lihua Jia, Jie Kang, Xiaoyang Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI and Robotics Ministry of Education Shanghai Engineering Research Center of AI and Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai200433 China Ji Hua Laboratory Guangdong Province Foshan528200 China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai200040 China Yiwu Research Institute of Fudan University Zhejiang Yiwu322000 China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou311121 China

The face of a humanoid robot can affect the user experience, and the detection of face preference is particularly important. Preference detection belongs to a branch of emotion recognition that has received much attention from researchers. Most of the previous preference detection studies have been conducted based on a single modality. In this paper, we detect face preferences of humanoid robots based on electroencephalogram (EEG) signals and eye movement signals for single modality, canonical correlation analysis fusion modality, and bimodal deep autoencoder (BDAE) fusion modality, respectively. We validated the theory of frontal asymmetry by analyzing the preference patterns of EEG and found that participants had higher alpha wave energy for preference faces. In addition, hidden preferences extracted by EEG signals were better classified than preferences from participants' subjective feedback, and also, the classification performance of eye movement data was improved. Finally, experimental results showed that BDAE multimodal fusion using frontal alpha and beta power spectral densities and eye movement information as features performed best, with the highest average accuracy of 83.13% for the SVM and 71.09% for the KNN. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Electroencephalography

Biomimetic Multi-UAV Swarm Exploration with U2U Communications Under Resource Constraints

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular Technology 2025年

作者： Huang, Yuanhao Wang, Hao Bai, Xuesong Cai, Xuan Yu, Haiyang Ren, Yilong Beihang University School of Transportation Science and Engineering Beijing100191 China State Key Lab of Intelligent Transportation System Beijing100191 China Dalian University of Technology School of Computer Science and Technology Dalian China Zhongguancun Laboratory Beijing100094 China

Existing multi-agent algorithms struggle with spatial coordination and require extensive prior environmental information for effective large-scale operation. This study introduces an innovative multi-UAV system that employs an evolutionary algorithm, reconceptualizing collaborative search tasks as a multi-objective cooperative challenge. Inspired by bacteria's stochastic exploration for pheromones, the algorithm utilizes pheromone concentration and gradient effects to enhance multi-source exploration's efficiency and robustness. A bespoke multi-UAV framework with UAV-to-UAV (U2U) communication was developed to implement and test the algorithm. Comprehensive experiments tested various chemotaxis strategies, guidance strengths, team sizes, and starting conditions, demonstrating the algorithm's consistent effectiveness in expansive terrains without relying on prior information. © 1967-2012 IEEE.

关键词： Stochastic systems

FEDGT: FEDERATED NODE CLASSIFICATION WITH SCAlabLE GRAPH TRANSFORMER

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Zaixi Hu, Qingyong Yu, Yang Gao, Weibo Liu, Qi Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Hong Kong University of Science and Technology Hong Kong

Graphs are widely used to model relational data. As graphs are getting larger and larger in real-world scenarios, there is a trend to store and compute subgraphs in multiple local systems. For example, recently proposed subgraph federated learning methods train Graph Neural Networks (GNNs) distributively on local subgraphs and aggregate GNN parameters with a central server. However, existing methods have the following limitations: (1) The links between local subgraphs are missing in subgraph federated learning. This could severely damage the performance of GNNs that follow message-passing paradigms to update node/edge features. (2) Most existing methods overlook the subgraph heterogeneity issue, brought by subgraphs being from different parts of the whole graph. To address the aforementioned challenges, we propose a scalable Federated Graph Transformer (FedGT) in the paper. Firstly, we design a hybrid attention scheme to reduce the complexity of the Graph Transformer to linear while ensuring a global receptive field with theoretical bounds. Specifically, each node attends to the sampled local neighbors and a set of curated global nodes to learn both local and global information and be robust to missing links. The global nodes are dynamically updated during training with an online clustering algorithm to capture the data distribution of the corresponding local subgraph. Secondly, FedGT computes clients' similarity based on the aligned global nodes with optimal transport. The similarity is then used to perform weighted averaging for personalized aggregation, which well addresses the data heterogeneity problem. Finally, extensive experimental results on 6 datasets and 2 subgraph settings demonstrate the superiority of FedGT. © 2024, CC BY.

关键词： Graph neural networks

Multi-Temporal Relationship Inference in Urban Areas

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Shuangli Zhou, Jingbo Liu, Ji Xu, Tong Chen, Enhong Xiong, Hui School of Computer Science and Technology University of Science and Technology of China Baidu Research China Business Intelligence Lab Baidu Research China Big Data Lab Baidu Research China School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology China

Finding multiple temporal relationships among locations can benefit a bunch of urban applications, such as dynamic offline advertising and smart public transport planning. While some efforts have been made on finding static relationships among locations, little attention is focused on studying time-aware location relationships. Indeed, abundant location-based human activities are time-varying and the availability of these data enables a new paradigm for understanding the dynamic relationships in a period among connective locations. To this end, we propose to study a new problem, namely multi-Temporal relationship inference among locations (Trial for short), where the major challenge is how to integrate dynamic and geographical influence under the relationship sparsity constraint. Specifically, we propose a solution to Trial with a graph learning scheme, which includes a spatially evolving graph neural network (SEENet) with two collaborative components: spatially evolving graph convolution module (SEConv) and spatially evolving self-supervised learning strategy (SE-SSL). SEConv performs the intra-time aggregation and inter-time propagation to capture the multifaceted spatially evolving contexts from the view of location message passing. In addition, SE-SSL designs time-aware self-supervised learning tasks in a global-local manner with additional evolving constraint to enhance the location representation © 2023, CC BY.

关键词： Location

Linear time approximation algorithm for column subset selection with local search 24

学校读者我要写书评

暂无评论

Linear time approximation algorithm for column subset select...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yuanbin Zou Ziyun Huang Jinhui Xu Jianxin Wang Qilong Feng School of Computer Science and Engineering Central South University Changsha China and Xiangjiang Laboratory Changsha China Department of Computer Science and Software Engineering Penn State Erie The Behrend College Department of Computer Science and Engineering State University of New York at Buffalo NY School of Computer Science and Engineering Central South University Changsha China and Xiangjiang Laboratory Changsha China and The Hunan Provincial Key Lab of Bioinformatics Central South University Changsha China

ISBN: (纸本)9798331314385

The Column Subset Selection (CSS) problem has been widely studied in dimensionality reduction and feature selection. The goal of the CSS problem is to output a submatrix S, consisting of k columns from an n × d input matrix A that minimizes the residual error ||A – SS† A||2F where S† is the Moore-Penrose inverse matrix of S. Many previous approximation algorithms have non-linear running times in both n and d, while the existing linear-time algorithms have a relatively larger approximation ratios. Additionally, the local search algorithms in existing results for solving the CSS problem are heuristic. To achieve linear running time while maintaining better approximation using a local search strategy, we propose a local search-based approximation algorithm for the CSS problem with exactly k columns selected. A key challenge in achieving linear running time with the local search strategy is how to avoid exhaustive enumerations of candidate columns for constructing swap pairs in each local search step. To address this issue, we propose a two-step mixed sampling method that reduces the number of enumerations for swap pair construction from O(dk) to k in linear time. Although the two-step mixed sampling method reduces the search space of local search strategy, bounding the residual error after swaps is a non-trivial task. To estimate the changes in residual error after swaps, we propose a matched swap pair construction method to bound the approximation loss, ensuring a constant probability of loss reduction in each local search step. In expectation, these techniques enable us to obtain the local search algorithm for the CSS problem with theoretical guarantees, where a 53(k + 1)-approximate solution can be obtained in linear running time O(ndk4 log k). Empirical experiments show that our proposed algorithm achieves better quality and time compared to previous algorithms on both small and large datasets. Moreover, it is at least 10 times faster than state-of-the-art algorith

关键词：