检索结果-内蒙古大学图书馆

Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fan, Yan Wang, Yu Zhu, Pengfei Hu, Qinghua 1Tianjin Key Lab of Machine Learning College of Intelligence and Computing Tianjin University China 2Haihe Laboratory of Information Technology Application Innovation China China

Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment challenging. In this work, we focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories. We provide a comprehensive analysis of SSCL and demonstrate that unreliable distributions of unlabeled data lead to unstable training and refinement of the progressing stages. This problem severely impacts the performance of SSCL. To address the limitations, we propose a novel approach called Dynamic Sub-Graph Distillation (DSGD) for semi-supervised continual learning, which leverages both semantic and structural information to achieve more stable knowledge distillation on unlabeled data and exhibit robustness against distribution bias. Firstly, we formalize a general model of structural distillation and design a dynamic graph construction for the continual learning progress. Next, we define a structure distillation vector and design a dynamic sub-graph distillation algorithm, which enables end-to-end training and adaptability to scale up tasks. The entire proposed method is adaptable to various CL methods and supervision settings. Finally, experiments conducted on three datasets CIFAR10, CIFAR100, and ImageNet-100, with varying supervision ratios, demonstrate the effectiveness of our proposed approach in mitigating the catastrophic forgetting problem in semi-supervised continual learning scenarios. Our code is available: https://***/fanyan0411/DSGD. Copyright © 2023, The Authors. All rights reserved.

关键词： Self-supervised learning

Design and development of intelligent well logging interpretation system 41

学校读者我要写书评

暂无评论

Design and development of intelligent well logging interpret...

第41届中国控制会议

作者： Saifei Ma Jin Tang Zerui Li Kun Li Wenjun Lv School of Computer Science and Technology Anhui University Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Key Laboratory of Multimodal Cognitive Computing Anhui University Institute of Advanced Technology University of Science and Technology of China Department of Automation University of Science and Technology of China

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In recent years,the traditional well logging interpretation method manually operated by experts has shown some problems,such as low efficiency and poor results,facing the challenges of high dimension,diversity and complexity of current logging *** the progress of artificial intelligence,its effectiveness and efficiency in logging interpretation have gradually attracted researchers' ***,the uncertainty of logging process necessitates the preprocess of collected logging data before employing the artificial intelligence ***,an intelligent well logging interpretation system is designed and developed in this *** the logging data anomalies may include data repetition,null value,etc.,a specific preprocessing module is designed in the system to tackle the data anomalies,so as to ensure that the data input into the algorithms is correct and *** governance can effectively enhance the effectiveness of data,so it is used to guide the design and implementation of logging interpretation ***,user mode and debug mode are designed to solve the problem of cross functional conflict in data governance.

关键词： System Development Logging Interpretation Data Governance Artificial intelligence

Efficient Explicit Joint-level Interaction Modeling with Mamba for Text-guided HOI Generation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Guohong Zeng, Ling-An Zheng, Zexin Gu, Shengbo Zheng, Wei-Shi Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

We propose a novel approach for generating text-guided human-object interactions (HOIs) that achieves explicit joint-level interaction modeling in a computationally efficient manner. Previous methods represent the entire human body as a single token, making it difficult to capture fine-grained joint-level interactions and resulting in unrealistic HOIs. However, treating each individual joint as a token would yield over twenty times more tokens, increasing computational overhead. To address these challenges, we introduce an Efficient Explicit Joint-level Interaction Model (EJIM). EJIM features a Dual-branch HOI Mamba that separately and efficiently models spatiotemporal HOI information, as well as a Dual-branch Condition Injector for integrating text semantics and object geometry into human and object motions. Furthermore, we design a Dynamic Interaction Block and a progressive masking mechanism to iteratively filter out irrelevant joints, ensuring accurate and nuanced interaction modeling. Extensive quantitative and qualitative evaluations on public datasets demonstrate that EJIM surpasses previous works by a large margin while using only 5% of the inference time. Code is available here. Copyright © 2025, The Authors. All rights reserved.

关键词： Geometry

Deep Generative Network for Image Inpainting with Gradient Semantics and Spatial-Smooth Attention

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Sheng, Ziqi Xu, Wenbo Lin, Cong Lu, Wei School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China Applied Laboratory of Dig Data and Education Statistics School of Statistics and Mathematics Guangdong University of Finance and Economics Guangzhou510006 China

As a powerful means of tampering in image content security area, image inpainting based on deep generative networks can yield visually appealing outputs but often produces ambiguous artifacts, particularly in boundary and high semantic areas. To address this issue, a novel end-to-end network with gradient semantics and spatial-smooth attention (GS-SSA) is proposed, which combines a gradient learning network and an image inpainting network. The gradient learning network is meant to properly anticipate the gradient semantics in the hole region and get a complete gradient semantic map. The image inpainting network utilizes the complete gradient semantic map to better repair the missing pixels and obtain the final inpainting results. Moreover, spatial-smooth attention is introduced into the image inpainting network, considering the spatial structural relations and the surrounding information in the hole region respectively. © 2023, The Authors. All rights reserved.

关键词： Semantics

HiMA: Hierarchical Quantum Microarchitecture for Qubit-Scaling and Quantum Process-Level Parallelism

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Qi Mei, Zi-Hao Shi, Han-Qing Guo, Liang-Liang Yang, Xiao-Yan Wang, Yun-Jie Xu, Xiao-Fan Xue, Cheng Kong, Wei-Cheng Wang, Jun-Chao Wu, Yu-Chun Chen, Zhao-Yun Guo, Guo-Ping CAS Key Laboratory of Quantum Information School of Physics University of Science and Technology of China Anhui Hefei230026 China Origin Quantum Computing Company Limited Anhui Hefei China Laboratory for Advanced Computing and Intelligence Engineering Henan Zhengzhou450001 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230088 China

Quantum computing holds immense potential for addressing a myriad of intricate challenges, which is significantly amplified when scaled to thousands of qubits. However, a major challenge lies in developing an efficient and scalable quantum control system. To address this, we propose a novel Hierarchical MicroArchitecture (HiMA) designed to facilitate qubit scaling and exploit quantum process-level parallelism. This microarchitecture is based on three core elements: (i) discrete qubit-level drive and readout, (ii) a process-based hierarchical trigger mechanism, and (iii) multiprocessing with a staggered triggering technique to enable efficient quantum process-level parallelism. We implement HiMA as a control system for a 72-qubit tunable superconducting quantum processing unit, serving a public quantum cloud computing platform, which is capable of expanding to 6144 qubits through three-layer cascading. In our benchmarking tests, HiMA achieves up to a 4.89× speedup under a 5-process parallel configuration. Consequently, to the best of our knowledge, we have achieved the highest CLOPS (Circuit Layer Operations Per Second), reaching up to 43,680, across all publicly available platforms. Copyright © 2024, The Authors. All rights reserved.

关键词： Qubits

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Pengxiang Gao, Zhi Zhang, Bofei Yuan, Tao Wu, Yuwei Harandi, Mehrtash Jia, Yunde Zhu, Song-Chun Li, Qing Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China State Key Laboratory of General Artificial Intelligence BIGAI China State Key Laboratory of General Artificial Intelligence Peking University China Department of Electrical and Computer System Engineering Monash University Australia Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Automation Tsinghua University China

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Fireclay

EKIGCN: External Knowledge Injected Graph Convolutional Networks for Aspect-based Sentiment Analysis

学校读者我要写书评

暂无评论

EKIGCN: External Knowledge Injected Graph Convolutional Netw...

IEEE International Conference on Cloud computing and intelligence Systems (CCIS)

作者： Xuefeng Shi Min Hu Fuji Ren Piao Shi Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China University of Electronic Science and Technology of China Chengdu Sichuan China

Aspect-based sentiment analysis (ABSA) is a challenging subtask in the natural language processing community, which aims to determine the sentiment polarity about the corresponding specific aspect terms. In existing works, external knowledge has been proven effective to improve the ABSA tasks’ performance. However, it is still essential to study further to find a universal method for ABSA tasks. Therefore, we propose an external knowledge-injected graph convolutional network (EKIGCN) to enhance the sentiment representation with commonsense. Specifically, Sentic Net is leveraged to provide external knowledge to construct an affective dependency graph. In order to fully exploit the effectiveness of affective knowledge, a shallow mutual interaction is utilized to fuse the learned contextual representation and the graph. Besides, to make EKIGCN sensitive to aspect terms, an aspect-aware multi-head attention module is also employed to enhance the corresponding relations between aspect and contextual words. Extensive experiments are conducted on three popular datasets to validate the effectiveness of our proposed model, and the results outperform the mentioned state-of-the-art methods in ABSA tasks.

关键词：

Exploiting Explicit and Inferred Implicit Personas for Multi-turn Dialogue Generation 10th

学校读者我要写书评

暂无评论

Exploiting Explicit and Inferred Implicit Personas for Multi...

10th CCF Conference on Natural Language Processing and Chinese computing, NLPCC 2021

作者： Wang, Ruifang He, Ruifang Wang, Longbiao Si, Yuke Liu, Huanyu Wang, Haocheng Dang, Jianwu State Key Laboratory of Communication Content Cognition People’s Daily Online Beijing China Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Japan Advanced Institute of Science and Technology Ishikawa Japan

ISBN: (纸本)9783030884796

Learning and utilizing personas in open-domain dialogue have become a hotspot in recent years. The existing methods that only use predefined explicit personas enhance the personality to some extent, however, they cannot easily avoid persona inconsistency and weak diversity responses. To address these problems, this paper proposes an effective model called Exploiting Explicit and Inferred Implicit Personas for Multi-turn Dialogue Generation (EIPD). Specifically, 1) an explicit persona extractor is designed to improve persona consistency;2) Taking advantage of the von Mises-Fisher (vMF) distribution in modeling directional data (e.g., the different persona state), we introduce the implicit persona inference to increase diversity;3) during the generation, the persona response generator fuses the explicit and implicit personas in the response. The experimental results on the ConvAI2 persona-chat dataset demonstrate that our model performs better than commonly used baselines. Further analysis of the ablation experiments shows that EIPD can generate more persona-consistent and diverse responses. © 2021, Springer Nature Switzerland AG.

关键词： Computers

Minimal Electrode EEG for BCI Emotion Detection 4

学校读者我要写书评

暂无评论

Minimal Electrode EEG for BCI Emotion Detection

4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024

作者： Li, Yuxin Fang, Hao Liu, Wen Cheng, Chuantong Chen, Hongda Xi'an Jiaotong-Liverpool University School of Advanced Technology Suzhou China The University of Edinburgh Institute for Imaging Data and Communications School of Engineering EdinburghEH9 3FG United Kingdom Chinese Academy of Sciences State Key Laboratory on Integrated Optoelectronics Institute of Semiconductors Beijing China Jiangsu Industrial Technology Research Institute Brain Machine Fusion Intelligence Institute Suzhou China

ISBN: (纸本)9798350394375

Electroencephalography (EEG)-based emotion recognition is a potential research direction in the field of brain-computer interfaces (BCIs). However, its deployment on wearable devices still suffers from the challenges of low accuracy, heavy computation, and complex electrode placement. This study focuses on advancing the efficiency and cost-effectiveness of EEG-based BCIs for emotion recognition. Our approach begins with an investigation of electrode placement in relation to emotion detection, leveraging the SEED dataset to identify an optimal configuration that uses a minimal number of electrodes while maintaining high recognition accuracy. Employing a variety of machine learning and deep learning algorithms, we compare detection accuracy across different electrode combinations. Through these experiments and subsequent analysis, we identify an effective combination of two electrodes, T7 and T8, with the SVM method achieving an impressive 92.8 % accuracy. This finding laid the foundation for the design of our wearable, closed-loop BCI device with EEG-based emotion recognition capability. © 2024 IEEE.

关键词： Emotion Recognition