检索结果-内蒙古大学图书馆

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-Sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Tianying Zhang, Lu Wang, Yang Guan, Jihong Fu, Yanwei Zhao, Jiajia Zhou, Shuigeng Department of Computer Science and Technology Tongji University Shanghai201804 China The Project Management Office of China National Scientific Seafloor Observatory Tongji University Shanghai200092 China Shanghai Key Lab of Intelligent Information Processing The School of Computer Science Fudan University Shanghai200438 China Shanghai Key Lab of Intelligent Information Processing The School of Data Science Fudan University Shanghai200433 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

The generic object detection (GOD) task has been successfully tackled by recent deep neural networks, trained by an avalanche of annotated training samples from some common classes. However, it is still non-trivial to generalize these object detectors to the novel long-tailed object classes, which have only few labeled training samples. To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans' ability of learning to learn, and intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes. Especially, the research in this emerging field has been flourishing in recent years with various benchmarks, backbones, and methodologies proposed. To review these FSOD works, there are several insightful FSOD survey articles [58, 59, 74, 78] that systematically study and compare them as the groups of fine-tuning/transfer learning, and meta-learning methods. In contrast, we review the existing FSOD algorithms from a new perspective under a new taxonomy based on their contributions, i.e., data-oriented, model-oriented, and algorithm-oriented. Thus, a comprehensive survey with performance comparison is conducted on recent achievements of FSOD. Furthermore, we also analyze the technical challenges, the merits and demerits of these methods, and envision the future directions of FSOD. Specifically, we give an overview of FSOD, including the problem definition, common datasets, and evaluation protocols. The taxonomy is then proposed that groups FSOD methods into three types. Following this taxonomy, we provide a systematic review of the advances in FSOD. Finally, further discussions on performance, challenges, and future directions are presented. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

Evaluating microbial protein elicitors for managing Cabbage Aphids in Brassica oleracea

学校读者我要写书评

暂无评论

Journal of Natural Pesticide Research 2024年 10卷

作者： Hameed, Muhammad Salman Basit, Abdul Humza, Muhammad Urooj, Nida Qasim, Muhammad Anwar, Muhammad State Key Laboratory of Green Pesticide International joint Research Center for Intelligent Biosensor Technology and Health Central China Normal University Wuhan 430079 China Guizhou Provincial Key Laboratory for Agricultural Pest Management of the Mountainous Region Scientific Observing and Experimental Station of Crop Pest in Guiyang Ministry of Agriculture and Rural Affairs Institute of Entomology Guizhou University Guiyang 550025 China Key Laboratory of Agro-products Quality and Safety Control in Storage and Transport Process Ministry of Agriculture and Rural Affairs/Institute of Food Science and Technology Chinese Academy of Agricultural Sciences Beijing 100193 China Department of Business Administrative Bahaudin Zakriya University Multan Pakistan Key Laboratory of Oasis Agricultural Pest Management and Plant Protection Utilization College of Agriculture Shihezi University Xinjiang Shihezi 832002 China Institute of Tropical Agriculture and Forestry Hainan University Haikou China

Cabbage (Brassica oleracea) is a globally important crop but often suffers from damage caused by sucking insect pests and various diseases. This study explores the effectiveness of microbial protein elicitors, such as PeaT1, PeBL1, Hrip1, and PeBA1, in managing Cabbage aphids (Brevicoryne brassicae). It investigates how these elicitors affect phytohormone pathways, including jasmonic acid, salicylic acid, and ethylene, and examines their impact on leaf structures, particularly trichomes. The research offers a novel approach by thoroughly assessing the mechanisms through which microbial protein elicitors control cabbage aphids. It provides valuable insights into potential new strategies for pest management in agriculture. By clarifying how elicitors interact with aphids, this study contributes to developing sustainable pest control and crop protection methods. © 2024 The Authors

关键词： Cabbage Aphids Gene expression and pest management Microbial protein elicitors Phytohormone pathways

The minority matters: a diversity-promoting collaborative 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

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative 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 Collaborative 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：

AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hou, Wenzheng Xu, Qianqian Yang, Zhiyong Bao, Shilong He, Yuan Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Alibaba Group Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen China

It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that the class distribution is overall balanced. However, long-tail datasets are ubiquitous in a wide spectrum of applications, where the amount of head class instances is larger than the tail classes. Under such a scenario, AUC is a much more reasonable metric than accuracy since it is insensitive toward class distribution. Motivated by this, we present an early trial to explore adversarial training methods to optimize AUC. The main challenge lies in that the positive and negative examples are tightly coupled in the objective function. As a direct result, one cannot generate adversarial examples without a full scan of the dataset. To address this issue, based on a concavity regularization scheme, we reformulate the AUC optimization problem as a saddle point problem, where the objective becomes an instance-wise function. This leads to an end-to-end training protocol. Furthermore, we provide a convergence guarantee of the proposed algorithm. Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem. Finally, the extensive experimental results show the performance and robustness of our algorithm in three long-tail datasets. © 2022, CC BY.

关键词： Deep learning

A mutual authentication lightweight rfid protocol for iot devices 2nd

学校读者我要写书评

暂无评论

A mutual authentication lightweight rfid protocol for iot de...

2nd International Cognitive Cities Conference, IC3 2019

作者： Lu, Yong Wang, Anxi Liu, Shuai School of Management Science and Engineering Nanjing University of Information Science and Technology Nanjing210044 China Guizhou Provincial Key Laboratory of Public Big Data GuiZhou University GuiyangGuizhou550025 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Guangzhou510632 China

ISBN: (纸本)9789811561122

The IoT data security is a hot topic at a data time. Personal privacy data may be easily leaked to data collectors in an open network environment. If the collectors get enough data, they can analyze the habit and interest of every IoT user, which may give helpful advice or cause endless harass. RFID authentication protocol in IoT is a powerful way to avoid the essential data leaked to data collectors. The previous protocols protect the security of RFID system. But they cannot guard the privacy of RFID system. The protocol we proposed achieves both the privacy and security. © Springer Nature Singapore Pte Ltd 2020.

关键词： Internet of things

Multi-criteria consensus sorting model with flexible linguistic preferences based on fuzzy information granulation from the perspective of preference disaggregation

学校读者我要写书评

暂无评论

Engineering Applications of Artificial Intelligence 2025年 154卷

作者： Zhang, Shiji Zhang, Shitao Tian, Hao Deveci, Muhammet Liu, Xiaodi School of Microelectronics and Data Science Anhui University of Technology Ma'anshan243032 China Key Laboratory of Multidisciplinary Management and Control of Complex Systems of Anhui Higher Education Institutes Anhui University of Technology Ma'anshan243002 China Anhui Provincial Joint Key Laboratory of Disciplines for Industrial Big Data Analysis and Intelligent Decision Ma'anshan243032 China Department of Industrial Engineering Turkish Naval Academy National Defence University Tuzla Istanbul34942 Turkey The Bartlett School of Sustainable Construction University College London LondonWC1E 6BT United Kingdom Department of Information Technologies Western Caspian University Baku1001 Azerbaijan

Multi-criteria group sorting (MCGS) that considers linguistic preferences involves multiple individuals evaluating alternatives and assigning them to pre-determined ordered categories based on specific criteria. Nevertheless, due to the limited availability of class information and the constrained cognitive capacity of decision-makers (DMs), it becomes challenging for DMs to furnish explicit preference information to reach consensus. Besides, decision parameters such as consensus threshold and class thresholds are also too hard to be assumed in advance. Therefore, this paper studies the preference disaggregation problem in MCGS, in which DMs are allowed to provide their pairwise comparisons in flexible linguistic expressions (FLEs) as preference information. To more fully utilize the preferences, semantic granulation is introduced. First, an individual consistency recognition model is proposed to identify inconsistent preferences and provide modification directions to the corresponding individuals. Next, semantic granulation and maximum entropy are combined into a granulation-driven information transformation model to convert the preference information based on FLEs into triangular fuzzy numbers (TFNs). Subsequently, in the consensus-driven preference disaggregation model, decision parameters and sorting results can be obtained at the premise of consensus by adjusting weights. Ultimately, to substantiate the effectiveness of the proposal, two numerical applications concerning the sorting of government venture capitals and information system suppliers are presented, along with comparative analysis, sensitivity analysis, and simulation analysis. © 2025 The Authors

关键词： Information granules

学校读者我要写书评

暂无评论

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Zhang, Hanyuan Zhang, Xingyu Jiang, Qize Zheng, Baihua Sun, Zhenbang Sun, Weiwei Wang, Changhu School of Computer Science Fudan University China Shanghai Key Laboratory of Data Science Fudan University China Shanghai Institute of Intelligent Electronics and Systems China Singapore Management University Singapore ByteDance AI Lab Beijing China

ISBN: (纸本)9780999241165

Trajectory similarity computation is a core problem in the field of trajectory data queries. However, the high time complexity of calculating the trajectory similarity has always been a bottleneck in real-world applications. Learning-based methods can map trajectories into a uniform embedding space to calculate the similarity of two trajectories with embeddings in constant time. In this paper, we propose a novel trajectory representation learning framework Traj2SimVec that performs scalable and robust trajectory similarity computation. We use a simple and fast trajectory simplification and indexing approach to obtain triplet training samples efficiently. We make the framework more robust via taking full use of the sub-trajectory similarity information as auxiliary supervision. Furthermore, the framework supports the point matching query by modeling the optimal matching relationship of trajectory points under different distance metrics. The comprehensive experiments on real-world datasets demonstrate that our model substantially outperforms all existing approaches. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Trajectories

学校读者我要写书评

暂无评论

Network Alignment

arXiv 2025年

作者： Tang, Rui Yong, Ziyun Jiang, Shuyu Chen, Xingshu Liu, Yaofang Zhang, Yi-Cheng Sun, Gui-Quan Wang, Wei School of Cyber Science and Engineering Sichuan University Chengdu610065 China Cyber Science Research Institute Sichuan University Chengdu610065 China Key Laboratory of Data Protection and Intelligent Management Ministry of Education Sichuan University Chengdu610065 China Department of Reproductive Technology The Affiliated Hospital of Southwest Medical University Luzhou646000 China Physics Department University of Fribourg Chemin du Musée 3 Fribourg1700 Switzerland Sino-Europe Complex Science Center School of Mathematics North University of China Shanxi Taiyuan030051 China Complex Systems Research Center Shanxi University Shanxi Taiyuan030006 China School of Public Health Chongqing Medical University Chongqing400016 China

Complex networks are frequently employed to model physical or virtual complex systems. When certain entities exist across multiple systems simultaneously, unveiling their corresponding relationships across the networks becomes crucial. This problem, known as network alignment, holds significant importance. It enhances our understanding of complex system structures and behaviours, facilitates the validation and extension of theoretical physics research about studying complex systems, and fosters diverse practical applications across various fields. However, due to variations in the structure, characteristics, and properties of complex networks across different fields, the study of network alignment is often isolated within each domain, with even the terminologies and concepts lacking uniformity. This review comprehensively summarizes the latest advance- © 2025, CC BY-NC-ND.

关键词： Large scale systems