检索结果-内蒙古大学图书馆

Application of CPU Parallel Computing in MATLAB Environment for analysis of Anti-Saturation and Gain Effects in PID Controller

学校读者我要写书评

暂无评论

Application of CPU Parallel Computing in MATLAB Environment ...

Data Driven Control and Learning Systems (DDCLS)

作者： Ruirui Huang Zhenhui Wu Yandong Hou Qianshuai Cheng Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China Technology and Media University of Henan Kaifeng Kaifeng China School of Artificial Intelligence Henan University Zhengzhou China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

With the continuous increase in data size and model complexity, the computational workload has grown rapidly, posing a significant challenge to the capabilities of computer data processing and simulation calculations. Therefore, parallel programming based on multicore and cluster architectures has become one of the mainstream technologies to enhance program execution efficiency and numerical computation efficiency. The theoretical foundations of parallel program computing have been applied in various aspects of engineering applications and theoretical simulations. In this paper, a new parallel PID anti-integral saturation controller is designed for a second-order closed-loop control system of unmanned aerial vehicles (UAVs). It compares and analyzes the runtime, execution efficiency, and speedup ratio of parallel programs and general serial programs under the same scenario. The experimental results demonstrate that parallel computing significantly improves the simulation program's efficiency for PID controller anti-saturation control systems under identical scenarios, exhibiting a high speedup ratio on the existing computing platform. Additionally, this study consolidates common issues encountered in MATLAB parallel program design, offering valuable insights into overcoming challenges in this domain.

关键词： Runtime Parallel programming Multicore processing Process control Parallel processing Control systems Central processing Unit

A Fast-trained and Generalized Spiking Neural Network for Robotic Gas Source Localization

学校读者我要写书评

暂无评论

A Fast-trained and Generalized Spiking Neural Network for Ro...

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Chiyang Liu Xinxing Chen Jian Huang Hubei Key Laboratory of Brain-inspired Intelligent Systems and the Key Laboratory for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Mobile robots for Gas Source Localization (GSL) tasks are a safer alternative than human and animal rescuers in hazardous scenarios. Existing research primarily concentrates on rule-based algorithms or conventional artificial neural networks (ANNs). However, these approaches are either inapplicable in cluttered environments or undeployable due to their high energy consumption and the demand for substantial computational resources. This paper introduces the application of energy-efficient spiking neural networks (SNNs) to address robotic GSL tasks. A pipeline is proposed to train SNNs with deep Q learning and a pretrain-finetune paradigm. To facilitate the training process, a small dataset of gas dispersion is generated utilizing openFoam and GADEN, a high-fidelity simulator for gas dispersion. Data from a simplified plume model are leveraged to pretrain an ANN, the activation function of which gradually transitions from a bounded rectified linear unit (bReLU) to a step function. Subsequently, an SNN initialized with the ANN parameters undergoes finetuning on the GADEN-based dataset. The training pipeline significantly reduces training time compared to direct training of SNNs. The trained SNN is validated within the GADEN simulation environment and compared to three different models, demonstrating promising performance and superior generalization despite limited training data.

关键词： Training Location awareness Q-learning Mechatronics Pipelines Training data Spiking neural networks Data models Mobile robots Dispersion

HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Huaxin Wang, Xiang Xu, Xiaohao Qing, Zhiwu Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China University of Michigan Ann Arbor United States

Point-supervised Temporal Action Localization (PSTAL) is an emerging research direction for label-efficient learning. However, current methods mainly focus on optimizing the network either at the snippet-level or the instance-level, neglecting the inherent reliability of point annotations at both levels. In this paper, we propose a Hierarchical Reliability Propagation (HR-Pro) framework, which consists of two reliability-aware stages: Snippet-level Discrimination Learning and Instance-level Completeness Learning, both stages explore the efficient propagation of high-confidence cues in point annotations. For snippet-level learning, we introduce an online-updated memory to store reliable snippet prototypes for each class. We then employ a Reliability-aware Attention Block to capture both intra-video and inter-video dependencies of snippets, resulting in more discriminative and robust snippet representation. For instance-level learning, we propose a point-based proposal generation approach as a means of connecting snippets and instances, which produces high-confidence proposals for further optimization at the instance level. Through multi-level reliability-aware learning, we obtain more reliable confidence scores and more accurate temporal boundaries of predicted proposals. Our HR-Pro achieves state-of-the-art performance on multiple challenging benchmarks, including an impressive average mAP of 60.3% on THUMOS14. Notably, our HR-Pro largely surpasses all previous point-supervised methods, and even outperforms several competitive fully-supervised methods. Code will be available at https://***/pipixin321/HR-Pro. Copyright © 2023, The Authors. All rights reserved.

关键词： Reliability

Saliency Regularization for Self-Training with Partial Annotations

学校读者我要写书评

暂无评论

Saliency Regularization for Self-Training with Partial Annot...

International Conference on Computer Vision (ICCV)

作者： Shouwen Wang Qian Wan Xiang Xiang Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan Research Institute of Posts and Telecommunications

Partially annotated images are easy to obtain in multi-label classification. However, unknown labels in partially annotated images exacerbate the positive-negative imbalance inherent in multi-label classification, which affects supervised learning of known labels. Most current methods require sufficient image annotations, and do not focus on the imbalance of the labels in the supervised training phase. In this paper, we propose saliency regularization (SR) for a novel self-training framework. In particular, we model saliency on the class-specific maps, and strengthen the saliency of object regions corresponding to the present labels. Besides, we introduce consistency regularization to mine unlabeled information to complement unknown labels with the help of SR. It is verified to alleviate the negative dominance caused by the imbalance, and achieve state-of-the-art performance on Pascal VOC 2007, MS-COCO, VG-200, and Openimages V3.

关键词：

Few-shot Action Recognition with Captioning Foundation Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Xiang Zhang, Shiwei Yuan, Hangjie Zhang, Yingya Gao, Changxin Zhao, Deli Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China Zhejiang University China

Transferring vision-language knowledge from pretrained multimodal foundation models to various downstream tasks is a promising direction. However, most current few-shot action recognition methods are still limited to a single visual modality input due to the high cost of annotating additional textual descriptions. In this paper, we develop an effective plug-and-play framework called CapFSAR to exploit the knowledge of multimodal models without manually annotating text. To be specific, we first utilize a captioning foundation model (i.e., BLIP) to extract visual features and automatically generate associated captions for input videos. Then, we apply a text encoder to the synthetic captions to obtain representative text embeddings. Finally, a visual-text aggregation module based on Transformer is further designed to incorporate cross-modal spatio-temporal complementary information for reliable few-shot matching. In this way, CapFSAR can benefit from powerful multimodal knowledge of pretrained foundation models, yielding more comprehensive classification in the low-shot regime. Extensive experiments on multiple standard few-shot benchmarks demonstrate that the proposed CapFSAR performs favorably against existing methods and achieves state-of-the-art performance. The code will be made publicly available. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

Improving Transferability of Adversarial Point Clouds with Model Commonalities

学校读者我要写书评

暂无评论

Improving Transferability of Adversarial Point Clouds with M...

IEEE International Conference on Cyborg and Bionic Systems (CBS)

作者： Junting Lv Lianguang Liu Yutong Zhang Depeng Li Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan China

Although deep learning of 3D point clouds has made significant progress, the robustness of 3D models has not been fully investigated. Existing 3D attack methods show satisfactory performance under the white-box setting but frequently suffer from a low transferability to attack black-box models. A key point to improve the transferability of attacks is to find the commonalities of multiple models. To this end, a novel attack method is proposed by only leveraging perturbations in local geometric feature areas termed FAP. Specifically, local perturbations are pertinently added by calculating the curvature to sample more points in the feature areas that 3D models potentially focus on. Moreover, to address the drawback of poor isometric robustness common to 3D models, we propose a generalized framework for diversifying input samples by adding random isometric transformations (DIT) in the attack process, which can be combined with other attack methods to improve their transferability. Evaluated on a variety of typical 3D models, the proposed attack method outperforms the current gradient-based methods in transferable black-box attacks, and the effectiveness of the proposed framework is demonstrated by extending it to other attack methods.

关键词： Point cloud compression Solid modeling Three-dimensional displays Shape Perturbation methods Closed box Focusing

Multimodal Brain-Computer Interfaces: AI-powered Decoding Methodologies

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Siyang Wang, Hongbin Chen, Xiaoqing Wu, Dongrui The Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Henan Key Laboratory of Brain Science and Brain Computer Interface Technology School of Electrical and Information Engineering Zhengzhou University China

Brain-computer interfaces (BCIs) enable direct communication between the brain and external devices. This review highlights the core decoding algorithms that enable multimodal BCIs, including a dissection of the elements, a unified view of diversified approaches, and a comprehensive analysis of the present state of the field. We emphasize algorithmic advancements in cross-modality mapping, sequential modeling, besides classic multi-modality fusion, illustrating how these novel AI approaches enhance decoding of brain data. The current literature of BCI applications on visual, speech, and affective decoding are comprehensively explored. Looking forward, we draw attention on the impact of emerging architectures like multimodal Transformers, and discuss challenges such as brain data heterogeneity and common errors. This review also serves as a bridge in this interdisciplinary field for experts with neuroscience background and experts that study AI, aiming to provide a comprehensive understanding for AI-powered multimodal BCIs. © 2025, CC BY-NC-ND.

关键词： Brain computer interface

Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qing, Zhiwu Zhang, Shiwei Wang, Jiayu Wang, Xiang Wei, Yujie Zhang, Yingya Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China Fudan University China

Despite diffusion models having shown powerful abilities to generate photorealistic images, generating videos that are realistic and diverse still remains in its infancy. One of the key reasons is that current methods intertwine spatial content and temporal dynamics together, leading to a notably increased complexity of text-to-video generation (T2V). In this work, we propose HiGen, a diffusion modelbased method that improves performance by decoupling the spatial and temporal factors of videos from two perspectives, i.e., structure level and content level. At the structure level, we decompose the T2V task into two steps, including spatial reasoning and temporal reasoning, using a unified denoiser. Specifically, we generate spatially coherent priors using text during spatial reasoning and then generate temporally coherent motions from these priors during temporal reasoning. At the content level, we extract two subtle cues from the content of the input video that can express motion and appearance changes, respectively. These two cues then guide the model's training for generating videos, enabling flexible content variations and enhancing temporal stability. Through the decoupled paradigm, HiGen can effectively reduce the complexity of this task and generate realistic videos with semantics accuracy and motion stability. Extensive experiments demonstrate the superior performance of HiGen over the state-of-the-art T2V methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

DFGET: Displacement-Field Assisted Graph Energy Transmitter for Gland Instance Segmentation

学校读者我要写书评

暂无评论

DFGET: Displacement-Field Assisted Graph Energy Transmitter ...

International Conference on Signal processing Proceedings (ICSP)

作者： Caiqing Jian Yongbin Qin Lihui Wang Chen Ye Xinyu Cheng GState Key Laboratory of Public Big Data College of Computer Science and Technology Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province Guizhou University Guiyang China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Gland instance segmentation is an essential but challenging task in the diagnosis of adenocarcinoma. The existing models usually achieve gland instance segmentation through multi-task learning and boundary loss constraint. However, how to deal with the problems of gland adhesion and inaccurate boundary in segmenting the complex samples remains a challenge. In this work, we propose a novel geometric feature named displacement field (DF), which can represent the geometric information such as shape, size, and orientation of the glands. Based on the explicit constraint of DF, a displacement-field assisted graph energy transmitter (DFGET) framework is proposed for solving the above problems. Using such graph framework, the gland semantic segmentation map and the displacement field of the graph nodes are estimated with two graph network branches. With the constraint of DF, a graph cluster module is presented to improve the intra-class feature consistency and inter-class feature discrepancy, as well as to separate the adherent glands. Extensive comparison and ablation experiments on the GlaS dataset demonstrate the effectiveness of the displacement field and the superiority of DFGET. Compared to the best comparative model, DFGET increases the object-Dice and object-F1 score by 2.27% and 3.11% respectively, while decreases the object-HD by 15.58, achieving state-of-the-art performance, which indicates that DFGET can serve as an auxiliary tool for the diagnosis of adenocarcinoma.

关键词： Instance segmentation Measurement Visualization Adhesives Shape Semantic segmentation Glands Signal processing algorithms Signal processing Market research