检索结果-内蒙古大学图书馆

Find Beauty in the Rare: Contrastive Composition Feature Clustering for Nontrivial Cropping Box Regression

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pan, Zhiyu Chen, Yinpeng Zhang, Jiale Lu, Hao Cao, Zhiguo Zhong, Weicai Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Huawei CBG Consumer Cloud Service Search Product & Big Data Platform Department China

Automatic image cropping algorithms aim to recompose images like human-being photographers by generating the cropping boxes with improved composition quality. Cropping box regression approaches learn the beauty of composition from annotated cropping boxes. However, the bias of annotations leads to quasi-trivial recomposing results, which has an obvious tendency to the average location of training samples. The crux of this predicament is that the task is naively treated as a box regression problem, where rare samples might be dominated by normal samples, and the composition patterns of rare samples are not well exploited. Observing that similar composition patterns tend to be shared by the cropping boundaries annotated nearly, we argue to find the beauty of composition from the rare samples by clustering the samples with similar cropping boundary annotations, i.e., similar composition patterns. We propose a novel Contrastive Composition Clustering (C2C) to regularize the composition features by contrasting dynamically established similar and dissimilar pairs. In this way, common composition patterns of multiple images can be better summarized, which especially benefits the rare samples and endows our model with better generalizability to render nontrivial results. Extensive experimental results show the superiority of our model compared with prior arts. We also illustrate the philosophy of our design with an interesting analytical visualization. Copyright © 2023, The Authors. All rights reserved.

关键词： image enhancement

Transmission-Constrained Consensus of Multiagent Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Xiaotian Su, Housheng School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China

This paper studies the consensus problem for multiagent systems with transmission constraints. A novel model of multiagent systems is proposed where the information transmissions between agents are disturbed by irregular distortions or interferences (named transmission constraint functions), and this model is universal which can be applied in many cases, such as interval consensus and discarded consensus. In the transmission-constrained consensus problem, we obtain the necessary and sufficient condition that agents can converge to state consensus. Furthermore, a more general case is studied in which the system reaches an equilibrium. Based on some techniques of algebraic topology and stability theory, the existence, uniqueness and stability of the system equilibrium point can be proven, which means the system can reach an asymptotically stable equilibrium. Moreover, the state values of the equilibrium are only decided by the network structure and transmission constraint functions, but not the agents’ initial states. Finally, numerical simulations are presented to illustrate the proposed theorems and corollaries. © 2022, CC BY-NC-SA.

关键词： Directed graphs

Fast Full-frame Video Stabilization with Iterative Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Weiyue Li, Xin Peng, Zhan Luo, Xianrui Ye, Xinyi Lu, Hao Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Albany AlbanyNY12222 United States

Video stabilization refers to the problem of transforming a shaky video into a visually pleasing one. The question of how to strike a good trade-off between visual quality and computational speed has remained one of the open challenges in video stabilization. Inspired by the analogy between wobbly frames and jigsaw puzzles, we propose an iterative optimization-based learning approach using synthetic datasets for video stabilization, which consists of two interacting submodules: motion trajectory smoothing and full-frame outpainting. First, we develop a two-level (coarse-to-fine) stabilizing algorithm based on the probabilistic flow field. The confidence map associated with the estimated optical flow is exploited to guide the search for shared regions through backpropagation. Second, we take a divide-and-conquer approach and propose a novel multiframe fusion strategy to render full-frame stabilized views. An important new insight brought about by our iterative optimization approach is that the target video can be interpreted as the fixed point of nonlinear mapping for video stabilization. We formulate video stabilization as a problem of minimizing the amount of jerkiness in motion trajectories, which guarantees convergence with the help of fixed-point theory. Extensive experimental results are reported to demonstrate the superiority of the proposed approach in terms of computational speed and visual quality. The code will be available on GitHub. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

Whale optimisation algorithm with role labour division for multimodal optimisation

学校读者我要写书评

暂无评论

International Journal of Innovative Computing and Applications 2024年第1期15卷 26-37页

作者： Wu, Bowen Xiao, Renbin School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China Institute of Artificial Intelligence Huazhong University of Science and Technology Hubei Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education of China Huazhong University of Science and Technology Hubei Wuhan430074 China

The multimodal optimisation problem challenges the balance between diversity and convergence, which poses a great degree of challenge to traditional population-based intelligence optimisers. The whale optimisation algorithm has the limitation of easily falling into local optimum when facing multimodal optimisation. To address this problem, this paper proposes a whale optimisation algorithm with role labour division (WOA-RDL). In WOA-RDL, a multi-stage role division of labour mechanism is designed to divide the optimisation process into two stages of group hunting. In the first stage, the task allocation in the hunting process is considered as two types of search tasks: exploration and exploitation. The external environmental stimulus of the task and the internal response threshold of the individual were designed to allow individuals to switch between exploration and exploitation tasks flexibly. In the second stage, the distribution mechanism of different roles was designed to simulate the 'strong to weak' distribution rule for the distribution of results after the hunt. The elite roles are selected to further strengthen their capabilities or remain robust, while the inferior roles are predicted and eliminated to improve the overall optimisation of the population and reduce the risk of falling into a local optimum. The results of the optimisation experiments using multimodal, unimodal, CEC2017 combined functions and CEC2009 dynamic functions to validate the effectiveness of the algorithm. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Optimization algorithms

SymmNeRF: Learning to Explore Symmetry Prior for Single-View View Synthesis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Xingyi Hong, Chaoyi Wang, Yiran Cao, Zhiguo Xian, Ke Lin, Guosheng Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of AIA Huazhong University of Science and Technology China S-Lab Nanyang Technological University Singapore

We study the problem of novel view synthesis of objects from a single image. Existing methods have demonstrated the potential in single-view view synthesis. However, they still fail to recover the fine appearance details, especially in self-occluded areas. This is because a single view only provides limited information. We observe that man-made objects usually exhibit symmetric appearances, which introduce additional prior knowledge. Motivated by this, we investigate the potential performance gains of explicitly embedding symmetry into the scene representation. In this paper, we propose SymmNeRF, a neural radiance field (NeRF) based framework that combines local and global conditioning under the introduction of symmetry priors. In particular, SymmNeRF takes the pixel-aligned image features and the corresponding symmetric features as extra inputs to the NeRF, whose parameters are generated by a hypernetwork. As the parameters are conditioned on the image-encoded latent codes, SymmNeRF is thus scene-independent and can generalize to new scenes. Experiments on synthetic and real-world datasets show that SymmNeRF synthesizes novel views with more details regardless of the pose transformation, and demonstrates good generalization when applied to unseen objects. Code is available at: https://***/xingyi-li/SymmNeRF. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Joint Masked Reconstruction and Contrastive Learning for Mining Interactions Between Proteins

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Jiang Wang, Xiaoping School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Institute of Artificial Intelligence Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Brain-Inspired Intelligent Systems Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Ministry of Education Wuhan430074 China

Protein-protein interaction (PPI) prediction is an instrumental means in elucidating the mechanisms underlying cellular operations, holding significant practical implications for the realms of pharmaceutical development and clinical treatment. Presently, the majority of research methods primarily concentrate on the analysis of amino acid sequences, while investigations predicated on protein structures remain in the nascent stages of exploration. Despite the emergence of several structure-based algorithms in recent years, these are still confronted with inherent challenges: (1) the extraction of intrinsic structural information of proteins typically necessitates the expenditure of substantial computational resources;(2) these models are overly reliant on seen protein data, struggling to effectively unearth interaction cues between unknown proteins. To further propel advancements in this domain, this paper introduces a novel PPI prediction method jointing masked reconstruction and contrastive learning, termed JmcPPI. This methodology dissects the PPI prediction task into two distinct phases: during the residue structure encoding phase, JmcPPI devises two feature reconstruction tasks and employs graph attention mechanism to capture structural information between residues;during the protein interaction inference phase, JmcPPI perturbs the original PPI graph and employs a multi-graph contrastive learning strategy to thoroughly mine extrinsic interaction information of novel proteins. Extensive experiments conducted on three widely utilized PPI datasets demonstrate that JmcPPI surpasses existing optimal baseline models across various data partition schemes. The associated code can be accessed via https://***/lijfrankopen/JmcPPI. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

A Parallel Read-Write Circuit Design for Driving Memristor Crossbar Array

学校读者我要写书评

暂无评论

A Parallel Read-Write Circuit Design for Driving Memristor C...

Neuromorphic Computing (ICNC), International Conference on

作者： Ningye Jiang Mingxuan Jiang Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

Memristor crossbar array is considered as a promising circuit module for accelerating neural networks. Because the memristor is tunable and multi-state, it is important to design applicable Read-Write (RW) circuit for driving memristor crossbar array. In this paper, a novel RW circuit based on analog circuits is proposed for tuning memristors in high-dimensional array parallelly, which is scalable and low-overhead. The standalone RW circuit schematic is presented for reading/writing single memristor and verified in circuit simulation. Then, we extend and apply this circuit into a two-dimensional memristor crossbar array. The performance of memristor crossbar array controlled by designed RW circuits is verified via the simulations under various machine learning datasets. The comparison with related works is presented, which demonstrates the advantages of the proposed RW circuit regarding overhead and anti-error.

关键词：

Distributed Resource Allocation via Accelerated Saddle Point Dynamics

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2021年第9期8卷 1588-1599页

作者： Wen-Ting Lin Yan-Wu Wang Chaojie Li Xinghuo Yu School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074 Key Laboratory of Image Processing and Intelligent Control Ministry of EducationHuazhong University of Science and TechnologyWuhan 430074China School of Electrical Engineering and Telecommunications University of New South WalesSydney NSW 2052Australia School of Engineering Royal Melbourne Institute of Technology(RMIT University)Melbourne VIC 3000Australia

In this paper,accelerated saddle point dynamics is proposed for distributed resource allocation over a multi-agent network,which enables a hyper-exponential convergence ***,an inertial fast-slow dynamical system with vanishing damping is introduced,based on which the distributed saddle point algorithm is *** dual variables are updated in two time scales,i.e.,the fast manifold and the slow *** the fast manifold,the consensus of the Lagrangian multipliers and the tracking of the constraints are pursued by the consensus *** the slow manifold,the updating of the Lagrangian multipliers is accelerated by inertial ***-exponential stability is defined to characterize a faster convergence of our proposed algorithm in comparison with conventional primal-dual algorithms for distributed resource *** simulation of the application in the energy dispatch problem verifies the result,which demonstrates the fast convergence of the proposed saddle point dynamics.

关键词： Accelerated saddle point dynamic distributed resource allocation hyper-exponential stability power dispatch

A Spatio-Temporal Scale Based Affective Neural Network for Emotion Detection in Conversation

学校读者我要写书评

暂无评论

A Spatio-Temporal Scale Based Affective Neural Network for E...

Chinese Automation Congress (CAC)

作者： Jiang Li Xiaoping Wang Shanglin Lei Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology (HUST) Wuhan China Institute of Artificial Intelligence Huazhong University of Science and Technology (HUST) Wuhan China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan China Key Laboratory of Brain-inspired Intelligent Systems Hubei Province Wuhan China

Emotion Detection in Conversation (EDC) has been implemented in numerous domains and is under increasing attention. The EDC task is highly challenging due to the need to incorporate both the context of the utterance and the identity of the participant. Some existing EDC approaches employ redundant network structures and inadequately model contextual utterances, resulting in limited performance gains. In this work, we devise a Spatio-Temporal scale based Affective neural Network (STANet) in a simplistic and efficacious manner. STANet consists of two main components, i.e., spatial scale network and temporal scale network, which are applied to extract spatial scale and temporal scale information in the conversation, respectively. Prior to spatio-temporal scale modeling, we encode the identity information of participants to examine its impact on the performance of emotion detection. We conduct substantial comparative experiments and ablation studies on three conversational emotion datasets, and the results demonstrate that our STANet realizes superior performance without taking advantage of external knowledge.

关键词：