检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Pengfei Min, Weiqing Song, Jiajun Zhang, Yang Jiang, Shuqiang The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The University of Chinese Academy of Sciences Beijing100049 China The Institute of Intelligent Computing Technology Chinese Academy of Sciences Suzhou215124 China

Food computing brings various perspectives to computer vision like vision-based food analysis for nutrition and health. As a fundamental task in food computing, food detection needs Zero-Shot Detection (ZSD) on novel unseen food objects to support real-world scenarios, such as intelligent kitchens and smart restaurants. Therefore, we first benchmark the task of Zero-Shot Food Detection (ZSFD) by introducing FOWA dataset with rich attribute annotations. Unlike ZSD, fine-grained problems in ZSFD like inter-class similarity make synthesized features inseparable. The complexity of food semantic attributes further makes it more difficult for current ZSD methods to distinguish various food categories. To address these problems, we propose a novel framework ZSFDet to tackle fine-grained problems by exploiting the interaction between complex attributes. Specifically, we model the correlation between food categories and attributes in ZSFDet by multi-source graphs to provide prior knowledge for distinguishing fine-grained features. Within ZSFDet, Knowledge-Enhanced Feature Synthesizer (KEFS) learns knowledge representation from multiple sources (e.g., ingredients correlation from knowledge graph) via the multi-source graph fusion. Conditioned on the fusion of semantic knowledge representation, the region feature diffusion model in KEFS can generate fine-grained features for training the effective zero-shot detector. Extensive evaluations demonstrate the superior performance of our method ZSFDet on FOWA and the widely-used food dataset UECFOOD-256, with significant improvements by 1.8% and 3.7% ZSD mAP compared with the strong baseline RRFS. Further experiments on PASCAL VOC and MS COCO prove that enhancement of the semantic knowledge can also improve the performance on general ZSD. Code and dataset are available at https://***/LanceZPF/KEFS. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features 38

Not All Diffusion Model Activations Have Been Evaluated as D...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Observation of quantum oscillations near the Mott-Ioffe-Regel limit in CaAs3

引用

National Science Review 2024年第12期11卷 122-133页

作者： Yuxiang Wang Minhao Zhao Jinglei Zhang Wenbin Wu Shichao Li Yong Zhang Wenxiang Jiang Nesta Benno Joseph Liangcai Xu Yicheng Mou Yunkun Yang Pengliang Leng Yong Zhang Li Pi Alexey Suslov Mykhaylo Ozerov Jan Wyzula Milan Orlita Fengfeng Zhu Yi Zhang Xufeng Kou Zengwei Zhu Awadhesh Narayan Dong Qian Jinsheng Wen Xiang Yuan Faxian Xiu Cheng Zhang State Key Laboratory of Surface Physics and Institute for Nanoelectronic Devices and Quantum Computing Fudan University State Key Laboratory of Surface Physics and Department of Physics Fudan University Anhui Province Key Laboratory of Condensed Matter Physics at Extreme Conditions High Magnetic Field Laboratory of the Chinese Academy of Sciences State Key Laboratory of Precision Spectroscopy East China Normal University National Laboratory of Solid State Microstructures and Department of Physics Nanjing University Key Laboratory of Artificial Structures and Quantum Control(Ministry of Education) School of Physics and Astronomy Shanghai Jiao Tong University Solid State and Structural Chemistry Unit Indian Institute of Science Wuhan National High Magnetic Field Center and School of Physics Huazhong University of Science and Technology School of Information Science and Technology Shanghai Tech University National High Magnetic Field Laboratory LNCMI-CNRS UPR3228 Université Grenoble Alpes International Center for Quantum Materials School of Physics Peking University School of Physics and Electronic Science East China Normal University Shanghai Center of Brain-Inspired Intelligent Materials and Devices East China Normal University Shanghai Qi Zhi Institute Zhangjiang Fudan International Innovation Center Fudan University Shanghai Research Center for Quantum Sciences

The Mott-Ioffe-Regel limit sets the lower bound of the carrier mean free path for coherent quasiparticle transport. Metallicity beyond this limit is of great interest because it is often closely related to quantum criticality and unconventional superconductivity. Progress along this direction mainly focuses on the strange-metal behaviors originating from the evolution of the quasiparticle scattering rate, such as linear-in-temperature resistivity, while the quasiparticle coherence phenomena in this regime are much less explored due to the short mean free path at the diffusive bound. Here we report the observation of quantum oscillations from Landau quantization near the Mott-Ioffe-Regel limit in CaAs3. Despite the insulator-like temperature dependence of resistivity, CaAs3presents giant magnetoresistance and prominent Shubnikov–de Haas oscillations from Fermi surfaces, indicating highly coherent band transport. In contrast,quantum oscillation is absent in the magnetic torque. The quasiparticle effective mass increases systematically with magnetic fields, manifesting a much larger value than what is expected based on magneto-infrared spectroscopy. This suggests a strong many-body renormalization effect near the Fermi surface. We find that these unconventional behaviors may be explained by the interplay between the mobility edge and the van Hove singularity, which results in the formation of coherent cyclotron orbits emerging at the diffusive bound. Our results call for further study on the electron correlation effect of the van Hove singularity.

关键词： Mott-Ioffe-Regel limit quantum oscillations van Hove singularity mobility edge

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Annotation for Face Anti-Spoofing

arXiv

引用

arXiv 2023年

作者： Chen, Xu Jia, Yunde Wu, Yuwei Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China

Face anti-spoofing plays a critical role in safeguarding facial recognition systems against presentation attacks. While existing deep learning methods show promising results, they still suffer from the lack of fine-grained annotations, which lead models to learn task-irrelevant or unfaithful features. In this paper, we propose a fine-grained annotation method for face anti-spoofing. Specifically, we first leverage the Segment Anything Model (SAM) to obtain pixel-wise segmentation masks by utilizing face landmarks as point prompts. The face landmarks provide segmentation semantics, which segments the face into regions. We then adopt these regions as masks and assemble them into three separate annotation maps: spoof, living, and background maps. Finally, we combine three separate maps into a three-channel map as annotations for model training. Furthermore, we introduce the Multi-Channel Region Exchange Augmentation (MCREA) to diversify training data and reduce overfitting. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches in both intra-dataset and cross-dataset evaluations. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks

arXiv

引用

arXiv 2025年

作者： Li, Yinqi Chang, Hong Hou, Ruibing Shan, Shiguang Chen, Xilin Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Diffusion models have shown remarkable progress in various generative tasks such as image and video generation. This paper studies the problem of leveraging pretrained diffusion models for performing discriminative tasks. Specifically, we extend the discriminative capability of pretrained frozen generative diffusion models from the classification task [1], [2] to the more complex object detection task, by "inverting" a pretrained layout-to-image diffusion model. To this end, a gradient-based discrete optimization approach for replacing the heavy prediction enumeration process, and a prior distribution model for making more accurate use of the Bayes’ rule, are proposed respectively. Empirical results show that this method is on par with basic discriminative object detection baselines on COCO dataset. In addition, our method can greatly speed up the previous diffusion-based method [1], [2] for classification without sacrificing accuracy. Code and models are available at https://***/LiYinqi/DIVE. © 2025, CC BY-NC-ND.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

No-Reference Image Quality Assessment Based on Active Reasoning Module 6

No-Reference Image Quality Assessment Based on Active Reason...

引用

6th IEEE International Conference on Electronic information and Communication technology, ICEICT 2023

作者： Qi, Junwei Deng, Yuhao Wang, Qingchun Yang, Zhen Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Shanghai Yanding Information Technology Co. Ltd. Shanghai201210 China College of Computer Science and Technology Harbin Engineering University Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9798350399059

We present a no-reference image-quality - assessment algorithm based on active reasoning module. This algorithm has three modules: the feature extraction module, the active reasoning module, and the quality assessment module. The active reasoning module incorporates the generator component of the generative adversarial network and enhances its structure with the Res2Net architecture. By integrating this module into the backbone feature extraction network, we improve the receptive field of each convolutional layer, enabling the network to capture information at different scales of the image. To preserve the texture information of the image, we input the gradient map of the distorted image, the distorted image itself, and the image features generated by the generator into the quality assessment module, which has a multi-feature regression networks. This module establishes a mapping model from image-feature to image-quality scores. We conducted experimental analysis of this algorithm on three widely used public datasets, confirming the excellent performance and superiorities of the presented algorithm. The results validate the effectiveness of the designed algorithm and its ability to assess image quality accurately. © 2023 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Video Anomaly Detection via Sequentially Learning Multiple Pretext Tasks

Video Anomaly Detection via Sequentially Learning Multiple P...

引用

International Conference on Computer Vision (ICCV)

作者： Chenrui Shi Che Sun Yuwei Wu Yunde Jia Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China

Learning multiple pretext tasks is a popular approach to tackle the nonalignment problem in unsupervised video anomaly detection. However, the conventional learning method of simultaneously learning multiple pretext tasks, is prone to sub-optimal solutions, incurring sharp performance drops. In this paper, we propose to sequentially learn multiple pretext tasks according to their difficulties in an ascending manner to improve the performance of anomaly detection. The core idea is to relax the learning objective by starting with easy pretext tasks in the early stage and gradually refine it by involving more challenging pretext tasks later on. In this way, our method is able to reduce the difficulties of learning and avoid converging to sub-optimal solutions. Specifically, we design a tailored sequential learning order for three widely-used pretext tasks. It starts with frame prediction task, then moves on to frame reconstruction task and last ends with frame-order classification task. We further introduce a new contrastive loss which makes the learned representations of normality more discriminative by pushing normal and pseudo-abnormal samples apart. Extensive experiments on three datasets demonstrate the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering 38

TFGDA: Exploring Topology and Feature Alignment in Semi-supe...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Dan, Jun Liu, Weiming Xie, Chunfeng Yu, Hua Dong, Shunjie Tan, Yanchao Zhejiang University China Queen Mary University of London United Kingdom Dalian University of Technology China Shanghai Jiao Tong University China Fuzhou University China Engineering Research Center of Big Data Intelligence Ministry of Education China Fujian Key Laboratory of Network Computing and Intelligent Information Processing China

Semi-supervised graph domain adaptation, as a branch of graph transfer learning, aims to annotate unlabeled target graph nodes by utilizing transferable knowledge learned from a label-scarce source graph. However, most existing studies primarily concentrate on aligning feature distributions directly to extract domain-invariant features, while ignoring the utilization of the intrinsic structure information in graphs. Inspired by the significance of data structure information in enhancing models' generalization performance, this paper aims to investigate how to leverage the structure information to assist graph transfer learning. To this end, we propose an innovative framework called TFGDA. Specially, TFGDA employs a structure alignment strategy named STSA to encode graphs' topological structure information into the latent space, greatly facilitating the learning of transferable features. To achieve a stable alignment of feature distributions, we also introduce a SDA strategy to mitigate domain discrepancy on the sphere. Moreover, to address the overfitting issue caused by label scarcity, a simple but effective RNC strategy is devised to guide the discriminative clustering of unlabeled nodes. Experiments on various benchmarks demonstrate the superiority of TFGDA over SOTA methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Noise Detection and Removal for Underground Communication Systems Based on L2 N onnal Inner Product

Noise Detection and Removal for Underground Communication Sy...

引用

IEEE International Conference on Artificial Intelligence in Engineering and technology (IICAIET)

作者： Bangwei Yu Yong Wang Liangang Qi Yang Liu College of Information and Communication Engineering Harbin Engineering University Harbin China Key Laboratory of Advanced Ship Communication and Information Technology Harbin Engineering University Harbin China Sichuan Key Laboratory of Agile Intelligent Computing Chengdu China

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

In underground communication systems, continuous mud pulse signals are susceptible to pump noise during transmission, resulting in a high bit error rate(BER). In this paper, a Normal Inner Product Orthogonal Matching Pursuit(NIPOMP) algorithm is proposed for the transmission characteristics of continuous waves in the underground. First, a cyclic prefix(CP) is added in front of the sent data. Then the observation vector is obtained by making a difference between the CP of the latter set of data and the CP of the former set of data. Then, the columns of the sensing matrix that are most correlated with the observation vectors are selected as candidate support sets by calculating the L2 norm. The least squares method was used to solve for the previous set of pump noise estimates. Finally, the pump noise is reconstructed using the correspondence between the time and frequency domains. This paper establishes a complete underground communication system. We discuss the noise characteristics of pump noise and analyze the denoising performance of the NIPOMP algorithm in depth. Simulation results show that the algorithm significantly reduces the system BER in complex channel environments with more drastic fading, including gas-phase, liquid-phase, gas-liquid two-phase, and liquid-solid two-channel environments.

关键词： Liquids Communication systems Simulation Oils Noise Noise reduction Matching pursuit algorithms Vectors Sensors Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Leveraging Knowledge Distillation for Improved Event Extraction in QA Models

Leveraging Knowledge Distillation for Improved Event Extract...

引用

Frontiers technology of information and Computer (ICFTIC), IEEE International Conference on

作者： Peiyao Zhou Zhikui Hu Kangli Zi Dawei Zhang School of Computer Science Jiangsu University of Science and Technology Zhenjiang China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Event extraction is an important task in natural language processing, and it is widely utilized in intelligence domains such as business and military for information extraction. Recently, many works have successfully transformed document-level event extraction into Question-answering (QA) tasks with remarkable results. This approach embeds event argument information within the questions, introducing prior knowledge into the process. Jin et al. highlighted the importance of high-quality QA pairs for practical QA tasks, emphasizing that constructing these pairs remains a key challenge[1]. In this study, we propose a Prompt-based question generation method to automatically generate questions containing event arguments, which converts event extraction into a QA task. We introduce an event ontology-based information retrieval module to enhance answer accuracy and select the most relevant document segments as input text. Additionally, we employ knowledge distillation to build the QA model, transferring knowledge from a large pre-trained model to a more compact and efficient one, improving the student model's performance. Experiments show that our model performs strongly in mainstream benchmarks, with 4.8 improvements on WikiEvents.

关键词： Accuracy Benchmark testing information retrieval Question generation Question answering (information retrieval) Data mining Business

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：