检索结果-内蒙古大学图书馆

The minority matters: a diversity-promoting collab.rative metric learning algorithm 22

学校读者我要写书评

暂无评论

The minority matters: a diversity-promoting collaborative me...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Shilong Bao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang State Key Laboratory of Information Security Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Laboratory of Big Data Mining and Knowledge Management CAS and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Collab.rative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collab.rative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collab.rative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a Diversity Control Regularization Scheme (DCRS) to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML.

关键词：

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

学校读者我要写书评

暂无评论

arXiv 2024年

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 availab.e at this url. © 2024, CC BY.

关键词： Semantics

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong 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 Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is availab.e at this url. © 2024, CC BY.

关键词：

Harnessing Hierarchical lab.l Distribution Variations in Test Agnostic Long-tail Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Zhiyong Xu, Qianqian Wang, Zitai Li, Sicong Han, Boyu Bao, Shilong Cao, Xiaochun Huang, Qingming School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS Institute of Information Engineering CAS School of Cyber Security University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China BDKM University of Chinese Academy of Sciences China

This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test lab.l distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be broken down hierarchically into global and local levels. The global ones reflect a broad range of diversity, while the local ones typically arise from milder changes, often focused on a particular neighbor. Traditional methods predominantly use a Mixture-of-Expert (MoE) approach, targeting a few fixed test lab.l distributions that exhibit substantial global variations. However, the local variations are left unconsidered. To address this issue, we propose a new MoE strategy, DirMixE, which assigns experts to different Dirichlet meta-distributions of the lab.l distribution, each targeting a specific aspect of local variations. Additionally, the diversity among these Dirichlet meta-distributions inherently captures global variations. This dual-level approach also leads to a more stable objective function, allowing us to sample different test distributions better to quantify the mean and variance of performance outcomes. Theoretically, we show that our proposed objective benefits from enhanced generalization by virtue of the variance-based regularization. Comprehensive experiments across multiple benchmarks confirm the effectiveness of DirMixE. The code is availab.e at https: //***/scongl/DirMixE. © 2024, CC BY.

关键词：

An intelligent self-sustained RAN slicing framework for diverse service provisioning in 5G-beyond and 6G networks

学校读者我要写书评

暂无评论

intelligent and Converged Networks 2020年第3期1卷 281-294页

作者： Jie Mei Xianbin Wang Kan Zheng Electrical and Computer Engineering Western UniversityLondonON N6A 5B9Canada Intelligent Computing and Communication(IC2)Lab Wireless Signal Processing and Network(WSPN)LabKey Laboratory of Universal Wireless CommunicationMinistry of EducationBeijing University of Posts and Telecommunications(BUPT)Beijing 100876China

Network slicing is a key technology to support the concurrent provisioning of heterogeneous Quality of Service(QoS)in the 5th Generation(5G)-beyond and the 6th Generation(6G)***,effective slicing of Radio Access Network(RAN)is very challenging due to the diverse QoS requirements and dynamic conditions in the 6G *** this paper,we propose a self-sustained RAN slicing framework,which integrates the self-management of network resources with multiple granularities,the self-optimization of slicing control performance,and self-learning together to achieve an adaptive control strategy under unforeseen network *** proposed RAN slicing framework is hierarchically structured,which decomposes the RAN slicing control into three levels,i.e.,network-level slicing,next generation NodeB(gNodeB)-level slicing,and packet scheduling level *** the network level,network resources are assigned to each gNodeB at a large timescale with coarse resource *** the gNodeB-level,each gNodeB adjusts the configuration of each slice in the cell at the large *** the packet scheduling level,each gNodeB allocates radio resource allocation among users in each network slice at a small ***,we utilize the transfer learning approach to enable the transition from a model-based control to an autonomic and self-learning RAN slicing *** the proposed RAN slicing framework,the QoS performance of emerging services is expected to be dramatically enhanced.

关键词： Radio Access Network(RAN) network slicing network resource management intelligent network

Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Chenglong Yang, Xiaobin Wang, Guohao Zheng, Aihua Tan, Chang Jia, Ruoran Tang, Jin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China iFLYTEK Co. Ltd. Hefei230088 China

License plate recognition plays a critical role in many practical applications, but license plates of large vehicles are difficult to be recognized due to the factors of low resolution, contamination, low illumination, and occlusion, to name a few. To overcome the above factors, the transportation management department generally introduces the enlarged license plate behind the rear of a vehicle. However, enlarged license plates have high diversity as they are non-standard in position, size, and style. Furthermore, the background regions contain a variety of noisy information which greatly disturbs the recognition of license plate characters. Existing works have not studied this challenging problem. In this work, we first address the enlarged license plate recognition problem and contribute a dataset containing 9342 images, which cover most of the challenges of real scenes. However, the created data are still insufficient to train deep methods of enlarged license plate recognition, and building large-scale training data is very time-consuming and high lab.r cost. To handle this problem, we propose a novel task-level disentanglement generation framework based on the Disentangled Generation Network (DGNet), which disentangles the generation into the text generation and background generation in an end-to-end manner to effectively ensure diversity and integrity, for robust enlarged license plate recognition. Extensive experiments on the created dataset are conducted, and we demonstrate the effectiveness of the proposed approach in three representative text recognition frameworks. © 2022, CC BY.

关键词： Optical character recognition

A Low SAR, Small size, High gain, Circularly polarized Antenna for Wearable Application 2

学校读者我要写书评

暂无评论

A Low SAR, Small size, High gain, Circularly polarized Anten...

2020 2nd International Conference on Artificial Intelligence Technologies and Application, ICAITA 2020

作者： Wang, Chao Zhang, Liang Cheng, Yi Li, XueMei Wu, Xianliang Key Lab of Ministry of Education of Intelligent Computing and Signal Processing Anhui University Hefei Anhui230601 China AnHui Province Key Laboratory of Simulation and Design for Electronic Information System Hefei Normal University Hefei Anhui230601 China

A planar, small size, high gain, low specific absorption rate (SAR) and circularly-polarized (CP) wearable antenna is proposed in this paper. The antenna is fabricated on a substrate with a dielectric constant of 3.5 with a thickness of 0.5 mm and sized at 42×42 mm only. Both the simulation results show that the overlap bandwidth of impedance and axial ratio of the proposed antenna is 13.7% (5.15-5.91 GHz). To isolate the antenna against the influence of the human body, a artificial magnetic conductor (AMC) plane is added on the reverse side of the radiator. The AMC structure effectively isolates the human body from the radiation of the antenna and reduces the specific absorption rate (SAR) of it by more than 96.1% at 5.5 GHz, which improves the antenna gain and the peak gain reaches 5.09 dBi at 5.5 GHz. The wearable performance of the antenna was analyzed, and it is observed that it can sustain good performance even under human body loading. Beside, the antenna has a small size, which makes it ideal for wearable applications. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Wearable antennas

A High Isolation UWB MIMO Antenna based on Angle Diversity

学校读者我要写书评

暂无评论

A High Isolation UWB MIMO Antenna based on Angle Diversity

IEEE International Wireless Symposium (IWS)

作者： Qin Li Yufa Sun Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (数字)9781728167039

ISBN: (纸本)9781728167046

A UWB MIMO antenna based on angle diversity technology is proposed in this paper. This antenna integrates Vivaldi antenna and UWB slot antenna with a compact size of 26×26mm 2 , the difference of radiation pattern can realize lower coupling between different antenna units. Less than -19 dB isolation between different ports can be obtained through the whole UWB band (3.1-10.6GHz). In addition, the combination of one C-Shaped structure and two L-Shaped structures (CLL) avoids the interference of WLAN (5.125-5.825GHz) band. The proposed antenna has good performance, which is suitable for UWB communication system.

关键词： Wireless LAN Slot antennas Vivaldi antennas Interference Ultra wideband antennas MIMO communication Antenna radiation patterns

A Novel EBG Power Plane Structure for Ultrawideband Suppression of SSN in High Speed Circuits

学校读者我要写书评

暂无评论

A Novel EBG Power Plane Structure for Ultrawideband Suppress...

Cross Strait Quad-Regional Radio Science and Wireless Technology Conference (CSQRWC)

作者： Yali Zhao Haoran Zhu Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (数字)9781728181813

ISBN: (纸本)9781728181820

A novel structure based on the coplanar electromagnetic band-gap (EBG) power plane is proposed to realize the ultrawideband suppression of simultaneous switching noise (SSN). The proposed EBG structure is realized with a combination of L-shaped Bridge and slit EBG structure which is inserted by a complementary split ring resonator (CSRR). From the simulated results of the proposed EBG structure, a wideband suppression of SSN ranges from 340 MHz to 20 GHz is achieved with a high mitigation level of -40 dB. Compared with the earlier published structures, the suppression effect is greatly improved.

关键词： Wireless communication Split ring resonators Switches Metamaterials Wideband Periodic structures Ultra wideband technology