检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： PanPan Chen DaHan Wang JiaHua Wu Yun Wu YiFan He XuYao Zhang ShunZhi Zhu Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology Xiamen China Xiamen Key Laboratory of Visual Perception Technology and Applications Reconova Technologies Co.Ltd Xiamen China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Click-based interactive image segmentation intends to segment an object from the background under user click guidance. Recently, Vision Transformer has made significant strides in interactive image segmentation. However, the previous studies 1) overlook the importance of different clicks in terms of their contribution to the segmentation results; and 2) suffer from inconsistency across different feature scales in the multi-scale structure. In this paper, we propose a new interactive segmentation framework, named RCFormer, with two novel components: reconstruct click patch embedding (RCPE) for encoding the importance of clicks, and multi-scale adaptive fusion (MSAF) for the adaptive fusion of feature maps across different scales. RCPE enhances the effectiveness of click interactions by spatially distinguishing the importance of clicks. MSAF adaptively fuses useful spatial information and filters the redundant feature at multi-scales. The experiments on several benchmarks show that our proposed approach achieves state-of-the-art performance. Notably, our method achieves 2.31 NoC@90 on the Berkeley dataset, improving by 8.6% over the previous best results.

关键词： Image segmentation Computer vision Filters Fuses Neural networks Network architecture Transformers

来源：评论

学校读者我要写书评

暂无评论

Beyond efficiency: molecular data pruning for enhanced generalization 24

Beyond efficiency: molecular data pruning for enhanced gener...

引用

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

作者： Dingshuo Chen Zhixun Li Yuyan Ni Guibin Zhang Ding Wang Qiang Liu Shu Wu Jeffrey XuYu Liang Wang New Laboratory of Pattern Recognition State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Academy of Mathematics and Systems Science Chinese Academy of Sciences Tongji University

ISBN: (纸本)9798331314385

With the emergence of various molecular tasks and massive datasets, how to perform efficient training has become an urgent yet under-explored issue in the area. Data pruning (DP), as an oft-stated approach to saving training burdens, filters out less influential samples to form a coreset for training. However, the increasing reliance on pretrained models for molecular tasks renders traditional in-domain DP methods incompatible. Therefore, we propose a Molecular data Pruning framework for enhanced Generalization (MolPeg), which focuses on the source-free data pruning scenario, where data pruning is applied with pretrained models. By maintaining two models with different updating paces during training, we introduce a novel scoring function to measure the informativeness of samples based on the loss discrepancy. As a plug-and-play framework, MolPeg realizes the perception of both source and target domain and consistently outperforms existing DP methods across four downstream tasks. Remarkably, it can surpass the performance obtained from full-dataset training, even when pruning up to 60-70% of the data on HIV and PCBA dataset. Our work suggests that the discovery of effective data-pruning metrics could provide a viable path to both enhanced efficiency and superior generalization in transfer learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Analysis of Kernel Ridgeless Regression with Asymmetric Kernel Learning

arXiv

引用

arXiv 2024年

作者： He, Fan He, Mingzhen Shi, Lei Huang, Xiaolin Suykens, Johan A.K. STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Leuven Belgium MOE Key Laboratory of System Control and Information Processing Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai200433 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China MOE Key Laboratory of System Control and Information Processing Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

Ridgeless regression has garnered attention among researchers, particularly in light of the "Benign Overfitting" phenomenon, where models interpolating noisy samples demonstrate robust generalization. However, kernel ridgeless regression does not always perform well due to the lack of flexibility. This paper enhances kernel ridgeless regression with Locally-Adaptive-Bandwidths (LAB) RBF kernels, incorporating kernel learning techniques to improve performance in both experiments and theory. For the first time, we demonstrate that functions learned from LAB RBF kernels belong to an integral space of Reproducible Kernel Hilbert Spaces (RKHSs). Despite the absence of explicit regularization in the proposed model, its optimization is equivalent to solving an 0-regularized problem in the integral space of RKHSs, elucidating the origin of its generalization ability. Taking an approximation analysis viewpoint, we introduce an lq-norm analysis technique (with 0 © 2024, CC BY.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey

arXiv

引用

arXiv 2024年

作者： Liu, Xuannan Cui, Xing Li, Peipei Li, Zekun Huang, Huaibo Xia, Shuhan Zhang, Miaoxuan Zou, Yueying He, Ran School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China School of Computer Science University of California Santa Barbara United States State Key Laboratory of Multimodal Artificial Intelligence Systems CASIA New Laboratory of Pattern Recognition CASIA School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China

The rapid evolution of multimodal foundation models has led to significant advancements in cross-modal understanding and generation across diverse modalities, including text, images, audio, and video. However, these models remain susceptible to jailbreak attacks, which can bypass built-in safety mechanisms and induce the production of potentially harmful content. Consequently, understanding the methods of jailbreak attacks and existing defense mechanisms is essential to ensure the safe deployment of multimodal generative models in real-world scenarios, particularly in security-sensitive applications. To provide comprehensive insight into this topic, this survey reviews jailbreak and defense in multimodal generative models. First, given the generalized lifecycle of multimodal jailbreak, we systematically explore attacks and corresponding defense strategies across four levels: input, encoder, generator, and output. Based on this analysis, we present a detailed taxonomy of attack methods, defense mechanisms, and evaluation frameworks specific to multimodal generative models. Additionally, we cover a wide range of input-output configurations, including modalities such as Any-to-Text, Any-to-Vision, and Any-to-Any within generative systems. Finally, we highlight current research challenges and propose potential directions for future research. The open-source repository corresponding to this work can be found at https://***/liuxuannan/Awesome-Multimodal-Jailbreak. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Oracle Character recognition using Unsupervised Discriminative Consistency Network

arXiv

引用

arXiv 2023年

作者： Wang, Mei Deng, Weihong Su, Sen The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China

Ancient history relies on the study of ancient characters. However, real-world scanned oracle characters are difficult to collect and annotate, posing a major obstacle for oracle character recognition (OrCR). Besides, serious abrasion and inter-class similarity also make OrCR more challenging. In this paper, we propose a novel unsupervised domain adaptation method for OrCR, which enables to transfer knowledge from labeled handprinted oracle characters to unlabeled scanned data. We leverage pseudo-labeling to incorporate the semantic information into adaptation and constrain augmentation consistency to make the predictions of scanned samples consistent under different perturbations, leading to the model robustness to abrasion, stain and distortion. Simultaneously, an unsupervised transition loss is proposed to learn more discriminative features on the scanned domain by optimizing both between-class and within-class transition probability. Extensive experiments show that our approach achieves state-of-the-art result on Oracle-241 dataset and substantially outperforms the recently proposed structure-texture separation network by 15.1%. © 2023, CC BY.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Activating More Pixels in Image Super-Resolution Transformer

Activating More Pixels in Image Super-Resolution Transformer

引用

Conference on Computer Vision and pattern recognition (CVPR)

作者： Xiangyu Chen Xintao Wang Jiantao Zhou Yu Qiao Chao Dong State Key Laboratory of Internet of Things for Smart City University of Macau Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory ARC Lab Tencent PCG

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SceneX: Procedural controllable Large-scale Scene Generation 39

SceneX: Procedural Controllable Large-scale Scene Generation

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Zhou, Mengqi Wang, Yuxi Hou, Jun Zhang, Shougao Li, Yiwei Luo, Chuanchen Peng, Junran Zhang, Zhaoxiang University of Chinese Academy of Sciences China Institute of Automation Chinese Academy of Sciences China State Key Laboratory of Multimodal Artificial Intelligence Systems China New Laboratory of Pattern Recognition China Centre for Artificial Intelligence and Robotics Malaysia China University of Geosciences Beijing China Shandong University China University of Science and Technology Beijing China

ISBN: (纸本)157735897X

Developing comprehensive explicit world models is crucial for understanding and simulating real-world scenarios. Recently, Procedural controllable Generation (PCG) has gained significant attention in large-scale scene generation by enabling the creation of scalable, high-quality assets. However, PCG faces challenges such as limited modular diversity, high expertise requirements, and challenges in managing the diverse elements and structures in complex scenes. In this paper, we introduce a large-scale scene generation framework, SceneX, which can automatically produce high-quality procedural models according to designers' textual descriptions. Specifically, the proposed method comprises two components, PCGHub and PCGPlanner. The former encompasses an extensive collection of accessible procedural assets and thousands of hand-craft API documents to perform as a standard protocol for PCG controller. The latter aims to generate executable actions for Blender to produce controllable and precise 3D assets guided by the user's instructions. Extensive experiments demonstrated the capability of our method in controllable large-scale scene generation, including nature scenes and unbounded cities, as well as scene editing such as asset placement and season translation. Copyright © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Split-net: Dual transformer encoder with splitting scene text image for script identification

引用

pattern recognition Letters 2025年 196卷 100-108页

作者： Ayush Roy Shivakumara Palaiahnakote Umapada Pal Cheng-Lin Liu Department of Computer Science and Engineering State University of New York Buffalo United States School of Science Engineering and Environment University of Salford Manchester United Kingdom Computer Vision and Pattern Recognition Indian Statistical Institute Kolkata India State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of the Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Script identification is vital for understanding scenes and video images. It is challenging due to high variations in physical appearance, typeface design, complex background, distortion, and significant overlap in the characteristics of different scripts. Unlike existing models, which aim to tackle the script images utilizing the scene text image as a whole, we propose to split the image into upper and lower halves to capture the intricate differences in stroke and style of various scripts. Motivated by the accomplishments of the transformer, a modified script-style-aware Mobile-Vision Transformer (M-ViT) is explored for encoding visual features of the images. To enrich the features of the transformer blocks, a novel Edge Enhanced Style Aware Channel Attention Module (EESA-CAM) has been integrated with M-ViT. Furthermore, the model fuses the features of the dual encoders (extracting features from the upper and the lower half of the images) by a dynamic weighted average procedure utilizing the gradient information of the encoders as the weights. In experiments on three standard datasets, MLe2e, CVSI2015, and SIW-13, the proposed model yielded superior performance compared to state-of-the-art models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Noise-Informed Diffusion-Generated Image Detection With Anomaly Attention

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5256-5268页

作者： Weinan Guan Wei Wang Bo Peng Ziwen He Jing Dong Haonan Cheng School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China New Laboratory of Pattern Recognition (NLPR) Institute of Automation Chinese Academy of Sciences (CASIA) Beijing China Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing China

With the rapid development of image generation technologies, especially the advancement of Diffusion Models, the quality of synthesized images has significantly improved, raising concerns among researchers about information security. To mitigate the malicious abuse of diffusion models, diffusion-generated image detection has proven to be an effective countermeasure. However, a key challenge for forgery detection is generalising to diffusion models not seen during training. In this paper, we address this problem by focusing on image noise. We observe that images from different diffusion models share similar noise patterns, distinct from genuine images. Building upon this insight, we introduce a novel Noise-Aware Self-Attention (NASA) module that focuses on noise regions to capture anomalous patterns. To implement a SOTA detection model, we incorporate NASA into Swin Transformer, forming an novel detection architecture NASA-Swin. Additionally, we employ a cross-modality fusion embedding to combine RGB and noise images, along with a channel mask strategy to enhance feature learning from both modalities. Extensive experiments demonstrate the effectiveness of our approach in enhancing detection capabilities for diffusion-generated images. When encountering unseen generation methods, our approach achieves the state-of-the-art performance.

关键词： Noise Diffusion models Forgery Noise reduction NASA Image reconstruction Transformers Training Image synthesis Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Gait Planning and Motion control Based on Vrep Simulation for Quadruped Robot

Gait Planning and Motion Control Based on Vrep Simulation fo...

引用

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Linqi Zhou Zhihua Chen Jun Liu Zhi Liu Yumeng Chen Liting Zhang key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition and MOE Key Lab of Nondestructive Testing Technology Nanchang Hangkong University Nanchang China State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing China

Gait planning of quadruped robots plays an important role in achieving less walking, including dynamic and static gait. In this article, a static and dynamic gait control method based on center of gravity stability margin is proposed. Firstly, the robot model and kinematics modeling are introduced. Secondly, the robot’s foot static and dynamic gait were planned and the foot trajectory was designed. Finally, two types of gait of the robot were simulated using Vrep simulation software, and the differences in stability and speed between the coordinated gait with speed and stability in the static and dynamic gait of a 12 degree of freedom robot were analyzed, verifying the effectiveness of the gait control method proposed in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：