检索结果-内蒙古大学图书馆

Towards Equitable Representation in Text-to-Image Synthesis Models with the Cross-Cultural Understanding Benchmark (CCUB) Dataset

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Zhixuan Shin, Youeun Okogwu, Beverley-Claire Yun, Youngsik Coleman, Lia Schaldenbrand, Peter Kim, Jihie Oh, Jean The Robotics Institute Carnegie Mellon University United States Department of Artificial Intelligence Dongguk University Korea Republic of

It has been shown that accurate representation in media improves the well-being of the people who consume it. By contrast, inaccurate representations can negatively affect viewers and lead to harmful perceptions of other cultures. To achieve inclusive representation in generated images, we propose a culturally-aware priming approach for text-to-image synthesis using a small but culturally curated dataset that we collected, known here as Cross-Cultural Understanding Benchmark (CCUB) Dataset, to fight the bias prevalent in giant datasets. Our proposed approach is comprised of two fine-tuning techniques: (1) Adding visual context via fine-tuning a pre-trained text-to-image synthesis model, Stable Diffusion, on the CCUB text-image pairs, and (2) Adding semantic context via automated prompt engineering using the fine-tuned large language model, GPT-3, trained on our CCUB culturally-aware text data. CCUB dataset is curated and our approach is evaluated by people who have a personal relationship with that particular culture. Our experiments indicate that priming using both text and image is effective in improving the cultural relevance and decreasing the offensiveness of generated images while maintaining quality. Our CCUB dataset and codes1 are publicly available. © 2023, CC BY-NC-ND.

关键词： Semantics

Informative Data Mining for One-shot Cross-Domain Semantic Segmentation

学校读者我要写书评

暂无评论

Informative Data Mining for One-shot Cross-Domain Semantic S...

International Conference on Computer Vision (ICCV)

作者： Yuxi Wang Jian Liang Jun Xiao Shuqi Mei Yuran Yang Zhaoxiang Zhang HKISI-CAS Centre for Artificial Intelligence and Robotics Chinese Academy of Sciences Institute of Automation University of Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Tencent

Contemporary domain adaptation offers a practical solution for achieving cross-domain transfer of semantic segmentation between labelled source data and unlabeled target data. These solutions have gained significant popularity; however, they require the model to be retrained when the test environment changes. This can result in unbearable costs in certain applications due to the time-consuming training process and concerns regarding data privacy. One-shot domain adaptation methods attempt to overcome these challenges by transferring the pre-trained source model to the target domain using only one target data. Despite this, the referring style transfer module still faces issues with computation cost and over-fitting problems. To address this problem, we propose a novel framework called Informative Data Mining (IDM) that enables efficient one-shot domain adaptation for semantic segmentation. Specifically, IDM provides an uncertainty-based selection criterion to identify the most informative samples, which facilitates quick adaptation and reduces redundant training. We then perform a model adaptation method using these selected samples, which includes patch-wise mixing and prototype-based information maximization to update the model. This approach effectively enhances adaptation and mitigates the overfitting problem. In general, we provide empirical evidence of the effectiveness and efficiency of IDM. Our approach outperforms existing methods and achieves a new state-of-the-art one-shot performance of 56.7%/55.4% on the GTA5/SYNTHIA to Cityscapes adaptation tasks, respectively. The code will be released at https://***/yxiwang/IDM.

关键词：

A Planning and Control Scheme for the Run-and-Jump Motion of a Wheeled Bipedal Robot Considering Dynamic Constraints

学校读者我要写书评

暂无评论

IEEE Transactions on Industrial Electronics 2025年

作者： Lu, Biao Cao, Haixin Hao, Yunsong Fang, Yongchun Tang, Shuang Nankai University Institute of Robotics and Automatic Information System College of Artificial Intelligence Tianiin Key Laboratory of Intelligent Robotics Tianjin300353 China Shenzhen Research Institute of Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen518083 China

Wheeled bipedal robots (WBRs) have recently drawn great attention due to their high movement efficiency and remarkable terrain adaptability. With the utilization of legs, they can adjust postures on uneven ground, as well as jump over obstacles or gaps. Nevertheless, compared to the extensive strategies for the balance control, the jumping motion of the WBRs has not received adequate research. In view of this, we propose a comprehensive planning and control scheme for the run-and-jump motion of WBRs, facilitating a seamless transition between running and jumping modalities. The motion is meticulously dissected into three stages: preparation, flight, and recovery, each characterized by a set of critical states at key transition points. These states are designed following an in-depth analysis of the run-and-jump objectives, ensuring compliance with the system dynamic constraints and consideration of the motor capacities. This methodology formulates an optimization problem, yielding reference trajectories that are pivotal for the execution of the run-and-jump motion. Based on reference trajectories, a customized motion library for the different run-and-jump motions is established, which alleviates the computational burden and ensures the versatility of the run-and-jump motion. Furthermore, the tracking controller, attitude adjustment controller, and impedance controller are developed separately to ensure the smoothness and stability of the overall run-andjump motion. The performance and effectiveness of the proposed scheme are first investigated through physical simulation and further validated by convincing hardware experiments. © 1982-2012 IEEE.

关键词： Motion planning

Data Adaptive Traceback for Vision-Language Foundation Models in Image Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Peng, Wenshuo Zhang, Kaipeng Yang, Yue Zhang, Hao Qiao, Yu OpenGVLab Shanghai AI Laboratory China Shanghai Jiao Tong University China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Vision-language foundation models have been incredibly successful in a wide range of downstream computer vision tasks using adaptation methods. However, due to the high cost of obtaining pre-training datasets, pairs with weak image-text correlation in the data exist in large numbers. We call them weak-paired samples. Due to the limitations of these weak-paired samples, the pre-training model are unable to mine all the knowledge from pre-training data. The existing adaptation methods do not consider the missing knowledge, which may lead to crucial task-related knowledge for the downstream tasks being ignored. To address this issue, we propose a new adaptation framework called Data Adaptive Traceback (DAT). Specifically, we utilize a zero-shot-based method to extract the most downstream task-related subset of the pre-training data to enable the downstream tasks. Furthermore, we adopt a pseudo-label-based semi-supervised technique to reuse the pre-training images and a vision-language contrastive learning method to address the confirmation bias issue in semi-supervised learning. We conduct extensive experiments that show our proposed DAT approach meaningfully improves various benchmark datasets performance over traditional adaptation methods by simply. Copyright © 2024, The Authors. All rights reserved.

关键词： Image classification

Design and Experiments of a Portable Robotic Ultrasound Scanning and Diagnosis System of Carotid Artery

学校读者我要写书评

暂无评论

Design and Experiments of a Portable Robotic Ultrasound Scan...

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Longyue Tan Zhaokun Deng Mingrui Hao Pengcheng Zhang Xilong Hou Xiaolin Gu Chen Chen Shuangyi Wang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Center for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Hong Kong Lingshu Medical Company Suzhou China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Ultrasound (US) imaging is an important, non-invasive method for evaluating the carotid artery (CA), which plays a critical role in early screening cardiovascular and cerebrovascular conditions. However, it requires specialized training for sonographers, which is a challenge in primary healthcare. Robotic devices now enable semi-automatic or fully automatic US scans, reducing the need for skilled operators. This paper presents an innovative, economically viable robotic system specifically engineered for conducting US examinations of the human CA. This system is distinguished by its advanced human-machine interaction capabilities with artificial intelligence assistance, which facilitate semi-automatic scanning processes in primary healthcare settings. Building upon this, the study introduces a semi-automatic scanning approach designed to control the device’s operations, aiming at capturing highquality images of the key structures of CA. Employing the images obtained through this method, the research proposes a segmentation strategy, leveraging fine-tuning adjustments on the LiteMedSAM model to achieve semantic segmentation of the CA in the images. The outcome is a nuanced diagnostic tool capable of identifying and evaluating carotid stenosis. The mentioned device and methods are tested on human subjects and the results indicate success on detecting critical vascular structures and positive feedback on human-machine interaction from operators and patients.

关键词： Human computer interaction Training Ultrasonic imaging Mechatronics Semantic segmentation Buildings Imaging Medical services Robots Carotid arteries

A graph-based two-stage classification network for mobile screen defect inspection

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2023年第2期24卷 203-216页

作者： Chaofan ZHOU Meiqin LIU Senlin ZHANG Ping WEI Badong CHEN State Key Laboratory of Industrial Control Technology Zhejiang UniversityHangzhou310027China College of Electrical Engineering Zhejiang UniversityHangzhou310027China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong UniversityXi’an710049China

Defect inspection,also known as defect detection,is significant in mobile screen quality *** are some challenging issues brought by the characteristics of screen defects,including the following:(1)the problem of interclass similarity and intraclass variation,(2)the difficulty in distinguishing low contrast,tiny-sized,or incomplete defects,and(3)the modeling of category dependencies for multi-label *** solve these problems,a graph reasoning module,stacked on a classification module,is proposed to expand the feature dimension and improve low-quality image features by exploiting category-wise dependency,image-wise relations,and interactions between *** further improve the classification performance,the classifier of the classification module is redesigned as a cosine similarity *** the help of contrastive learning,the classification module can better initialize the category-wise graph of the reasoning *** on the mobile screen defect dataset show that our two-stage network achieves the following best performances:97.7%accuracy and 97.3%*** proves that the proposed approach is effective in industrial applications.

关键词： Graph-based methods Multi-label classification Mobile screen defects Neural networks

PWISEG: POINT-BASED WEAKLY-SUPERVISED INSTANCE SEGMENTATION FOR SURGICAL INSTRUMENTS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Zhen Xu, Huan Wu, Jinlin Chen, Zhen Lei, Zhen Liu, Hongbin Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong

In surgical procedures, correct instrument counting is essential. Instance segmentation is a location method that locates not only an object’s bounding box but also each pixel’s specific details. However, obtaining mask-level annotations is labor-intensive in instance segmentation. To address this issue, we propose a novel yet effective weakly-supervised surgical instrument instance segmentation approach, named Point-based Weakly-supervised Instance Segmentation (PWISeg). PWISeg adopts an FCN-based architecture with point-to-box and point-to-mask branches to model the relationships between feature points and bounding boxes, as well as feature points and segmentation masks on FPN, accomplishing instrument detection and segmentation jointly in a single model. Since mask level annotations are hard to available in the real world, for point-to-mask training, we introduce an unsupervised projection loss, utilizing the projected relation between predicted masks and bboxes as supervision signal. On the other hand, we annotate a few pixels as the key pixel for each instrument. Based on this, we further propose a key pixel association loss and a key pixel distribution loss, driving the point-to-mask branch to generate more accurate segmentation predictions. To comprehensively evaluate this task, we unveil a novel surgical instrument dataset with manual annotations, setting up a benchmark for further research. Our comprehensive research trial validated the superior performance of our PWISeg. The results show that the accuracy of surgical instrument segmentation is improved, surpassing most methods of instance segmentation via weakly supervised bounding boxes. This improvement is consistently observed in our proposed dataset and when applied to the public HOSPI-Tools dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Pixels

PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gao, Ning Zhou, Sanping Wang, Le Zheng, Nanning National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Semi-supervised learning has emerged as a widely adopted technique in the field of medical image segmentation. The existing works either focuses on the construction of consistency constraints or the generation of pseudo labels to provide high-quality supervisory signals, whose main challenge mainly comes from how to keep the continuous improvement of model capabilities. In this paper, we propose a simple yet effective semi-supervised learning framework, termed Progressive Mean Teachers (PMT), for medical image segmentation, whose goal is to generate high-fidelity pseudo labels by learning robust and diverse features in the training process. Specifically, our PMT employs a standard mean teacher to penalize the consistency of the current state and utilizes two sets of MT architectures for co-training. The two sets of MT architectures are individually updated for prolonged periods to maintain stable model diversity established through performance gaps generated by iteration differences. Additionally, a difference-driven alignment regularizer is employed to expedite the alignment of lagging models with the representation capabilities of leading models. Furthermore, a simple yet effective pseudo-label filtering algorithm is employed for facile evaluation of models and selection of high-fidelity pseudo-labels outputted when models are operating at high performance for co-training purposes. Experimental results on two datasets with different modalities, i.e., CT and MRI, demonstrate that our method outperforms the state-of-the-art medical image segmentation approaches across various dimensions. The code is available at https://***/Axi404/PMT. © 2024, CC BY.

关键词： Self-supervised learning

Driver Intention Prediction Using Text Prompts with In-Cabin and Out-Cabin Cameras

学校读者我要写书评

暂无评论

Driver Intention Prediction Using Text Prompts with In-Cabin...

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Bin He Ningmei Yu Hongcheng Han School of Automation and Information Engineering Xi'an University of Technology Xi’an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi’an China

ISBN: (数字)9798331506896

ISBN: (纸本)9798331506902

Human-machine collaborative driving is poised to become a cornerstone of intelligent transportation systems, where accurate recognition of driver behavior and intent is crucial for vehicle decision-making and real-time traffic management. Existing methods for driver maneuver recognition, primarily based on 3D convolutional neural networks (3D-CNNs) and Transformers, encounter challenges such as spatiotemporal redundancy, limited spatial perception, and inadequate capture of detailed object motion. To overcome these limitations, we propose a novel text-driven approach utilizing Large Language Models (LLMs) for driver maneuver recognition. By integrating textual semantics from both in-car and external environments, the Contrastive Language–Image Pre-training (CLIP) text encoder enhances the model's comprehension of complex video scenarios, improving both training and inference efficiency while enabling more precise identification of motion dynamics. Experimental results demonstrate that our approach outperforms state-of-the-art methods in driver intention prediction.

关键词： Training Accuracy Three-dimensional displays Target recognition Large language models Redundancy Transformers Spatiotemporal phenomena Vehicle dynamics Vehicles