检索结果-内蒙古大学图书馆

CATVTON: CONCATENATION IS ALL YOU NEED FOR VIRTUAL TRY-ON WITH DIFFUSION MODELS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chong, Zheng Dong, Xiao Li, Haoxiang Zhang, Shiyue Zhang, Wenqing Zhang, Xujie Zhao, Hanqing Jiang, Dongmei Liang, Xiaodan Shenzhen Campus of Sun Yat-sen University Guangdong Shenzhen518107 China School of Artificial Intelligence Sun Yat-sen University Zhuhai Campus Zhuhai519082 China Pixocial Technology Pengcheng Laboratory China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China

Virtual try-on methods based on diffusion models achieve realistic effects but often require additional encoding modules, a large number of training parameters, and complex preprocessing, which increases the burden on training and inference. In this work, we re-evaluate the necessity of additional modules and analyze how to improve training efficiency and reduce redundant steps in the inference process. Based on these insights, we propose CatVTON, a simple and efficient virtual try-on diffusion model that transfers in-shop or worn garments of arbitrary categories to target individuals by concatenating them along spatial dimensions as inputs of the diffusion model. The efficiency of CatVTON is reflected in three aspects: (1) Lightweight network. CatVTON consists only of a VAE and a simplified denoising UNet, removing redundant image and text encoders as well as cross-attentions, and includes just 899.06M parameters. (2) Parameter-efficient training. Through experimental analysis, we identify self-attention modules as crucial for adapting pre-trained diffusion models to the virtual try-on task, enabling high-quality results with only 49.57M training parameters. (3) Simplified inference. CatVTON eliminates unnecessary preprocessing, such as pose estimation, human parsing, and captioning, requiring only person image and garment reference to guide the virtual try-on process, reducing 49%+ memory usage compared to other diffusion-based methods. Extensive experiments demonstrate that CatVTON achieves superior qualitative and quantitative results compared to baseline methods and demonstrates strong generalization performance in in-the-wild scenarios, despite being trained solely on public datasets with 73K *** Codes 68T42 (Primary) 168T45 (Secondary) © 2024, CC BY-NC-SA.

关键词： Signal encoding

Counterfactual data Augmentation with Denoising Diffusion for Graph Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiao, Chunjing Pang, Shikang Xu, Xovee Li, Xuan Trajcevski, Goce Zhou, Fan The School of Computer and Information Engineering Henan University China The Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China The University of Electronic Science and Technology of China Sichuan Chengdu610054 China The National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Chengdu610065 China The Department of Electrical and Computer Engineering Iowa State University AmesIA50011 United States

A critical aspect of Graph Neural Networks (GNNs) is to enhance the node representations by aggregating node neighborhood information. However, when detecting anomalies, the representations of abnormal nodes are prone to be averaged by normal neighbors, making the learned anomaly representations less distinguishable. To tackle this issue, we propose CAGAD - an unsupervised Counterfactual data Augmentation method for Graph Anomaly Detection - which introduces a graph pointer neural network as the heterophilic node detector to identify potential anomalies whose neighborhoods are normal-node-dominant. For each identified potential anomaly, we design a graph-specific diffusion model to translate a part of its neighbors, which are probably normal, into anomalous ones. At last, we involve these translated neighbors in GNN neighborhood aggregation to produce counterfactual representations of anomalies. Through aggregating the translated anomalous neighbors, counterfactual representations become more distinguishable and further advocate detection performance. The experimental results on four datasets demonstrate that CAGAD significantly outperforms strong baselines, with an average improvement of 2.35% on F1, 2.53% on AUC-ROC, and 2.79% on AUC-PR. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

Graph Chirp Signal and Graph Fractional Vertex-Frequency Energy Distribution

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Cui, Manjun Zhang, Zhichao School of Mathematics and Statistics The Center for Applied Mathematics of Jiangsu Province The Jiangsu International Joint Laboratory on System Modeling and Data Analysis Nanjing University of Information Science and Technology Nanjing210044 China School of Mathematics and Statistics Nanjing University of Information Science and Technology Nanjing210044 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Computational Science and Application of Hainan Province Hainan Normal University Haikou571158 China

Graph signal processing (GSP) has emerged as a powerful framework for analyzing data on irregular domains. In recent years, many classical techniques in signal processing (SP) have been successfully extended to GSP. Among them, chirp signals play a crucial role in various SP applications. However, graph chirp signals have not been formally defined despite their importance. Here, we define graph chirp signals and establish a comprehensive theoretical framework for their analysis. We propose the graph fractional vertex-frequency energy distribution (GFED), which provides a powerful tool for processing and analyzing graph chirp signals. We introduce the general fractional graph distribution (GFGD), a generalized vertex-frequency distribution, and the reduced interference GFED, which can suppress cross-term interference and enhance signal clarity. Furthermore, we propose a novel method for detecting graph signals through GFED domain filtering, facilitating robust detection and analysis of graph chirp signals in noisy environments. Moreover, this method can be applied to real-world data for denoising more effective than some state-of-the-arts, further demonstrating its practical significance. Copyright © 2025, The Authors. All rights reserved.

关键词： Wiener filtering

LogicalFactChecker: Leveraging logical operations for fact checking with graph module network 58

学校读者我要写书评

暂无评论

LogicalFactChecker: Leveraging logical operations for fact c...

58th Annual Meeting of the Association for Computational Linguistics, ACL 2020

作者： Zhong, Wanjun Tang, Duyu Feng, Zhangyin Duan, Nan Zhou, Ming Gong, Ming Shou, Linjun Jiang, Daxin Wang, Jiahai Yin, Jian The School of Data and Computer Science Sun Yat-Sen University Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Microsoft Corporation Harbin Institute of Technology

ISBN: (纸本)9781952148255

Verifying the correctness of a textual statement requires not only semantic reasoning about the meaning of words, but also symbolic reasoning about logical operations like count, superlative, aggregation, etc. In this work, we propose LogicalFactChecker, a neural network approach capable of leveraging logical operations for fact checking. It achieves the state-of-the-art performance on TABFACT, a large-scale, benchmark dataset built for verifying a textual statement with semi-structured tables. This is achieved by a graph module network built upon the Transformer-based architecture. With a textual statement and a table as the input, LogicalFactChecker automatically derives a program (a.k.a. logical form) of the statement in a semantic parsing manner. A heterogeneous graph is then constructed to capture not only the structures of the table and the program, but also the connections between inputs with different modalities. Such a graph reveals the related contexts of each word in the statement, the table and the program. The graph is used to obtain graph-enhanced contextual representations of words in Transformer-based architecture. After that, a program-driven module network is further introduced to exploit the hierarchical structure of the program, where semantic compositionality is dynamically modeled along the program structure with a set of function-specific modules. Ablation experiments suggest that both the heterogeneous graph and the module network are important to obtain strong results. © 2020 Association for Computational Linguistics

关键词： Semantics

Decomposed Neural Architecture Search for image denoising

学校读者我要写书评

暂无评论

Applied Soft Computing 2022年 124卷

作者： Li, Di Bai, Yunpeng Bai, Zongwen Li, Ying Shang, Changjing Shen, Qiang School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northwestern Polytechnical University Xi'an710129 China Department of Computer Science Faculty of Business and Physical Sciences Aberystwyth University AberystwythSY233DB United Kingdom Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data School of Physics and Electronic Information Yan'an University Yan'an716000 China

In practical applications of deep learning, as the demand for the modeling capability increases, the network size may need to be massively enlarged in response. This may form a significant challenge in practice, especially when facing the dilemma of limited computational resources, making model compression indispensable. It can be time-consuming and interminable to obtain an appropriate network architecture through manual compression. In this paper, we propose an automated method for searching decomposed network architectures, named DNAS (standing for Decomposed Neural Architecture Search). It integrates both tasks of neural architecture search and tensor decomposition based model compression within a unified framework. The method is able to efficiently find a compact network with high performance for image denoising, with respect to memory and runtime. Particularly, using one single V100 GPU, it only takes about 1.5 h to obtain a denoising network on the BSD500 dataset. Experimental results demonstrate that compared with models developed using existing methods, DNAS consumes significantly less inference time and employs much fewer trainable parameters, outperforming existing approaches on both synthetic and real-world denoising datasets. © 2022 Elsevier B.V.

关键词： Network architecture

Online Multiple Object Tracking with Reid Feature Extraction Network and Similarity Matrix Network 5

学校读者我要写书评

暂无评论

Online Multiple Object Tracking with Reid Feature Extraction...

2020 5th International Conference on Intelligent Computing and Signal processing, ICSP 2020

作者： Ji, Qingge Yu, Haoqiang School of Data and Computer Science Sun Yat-sen University Guangzhou510006 China Guangdong Province Key Laboratory Big Data Analysis and Processing Guangzhou510006 China

In multiple object tracking(MOT), data association is a crucial part. By constructing similarity loss matrix for trajectories and detections, they can be matched correspondingly by using Hungarian matching algorithm. However, the similarity loss is often obtained by calculating the Euclidean distance or other handcraft distance metrics of features extracted between objects, which may not be robust enough, resulting in matching inaccuracy. In this paper, we propose a novel MOT method with applying deep learning to feature extraction and data association. We firstly design the appearance feature extraction network(AFN) to learn effective features by training it on a large-scale person re-identification dataset(reid). Then, we propose the similarity matrix estimation network (SMN) to obtain reliable similarity by training it on the public MOT Challenge dataset, MOT17. Additionally, the similarity matrix output of SMN includes the dummy objects, which are used to deal with the association problems of object missing and object appearance between frames. In the end, our proposed MOT method is evaluated on MOT15, MOT17 and ablation study is carried out. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Feature extraction

UniXcoder: Unified Cross-Modal Pre-training for Code Representation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Guo, Daya Lu, Shuai Duan, Nan Wang, Yanlin Zhou, Ming Yin, Jian School Of Computer Science And Engineering Sun Yat-sen University Guangdong Key Laboratory Of Big Data Analysis And Processing Guangzhou China Microsoft Research Asia Beijing China Langboat Technology Beijing China

Pre-trained models for programming languages have recently demonstrated great success on code intelligence. To support both code-related understanding and generation tasks, recent works attempt to pre-train unified encoder-decoder models. However, such encoder-decoder framework is sub-optimal for auto-regressive tasks, especially code completion that requires a decoder-only manner for efficient inference. In this paper, we present UniXcoder, a unified cross-modal pre-trained model for programming language. The model utilizes mask attention matrices with prefix adapters to control the behavior of the model and leverages cross-modal contents like AST and code comment to enhance code representation. To encode AST that is represented as a tree in parallel, we propose a one-to-one mapping method to transform AST in a sequence structure that retains all structural information from the tree. Furthermore, we propose to utilize multi-modal contents to learn representation of code fragment with contrastive learning, and then align representations among programming languages using a cross-modal generation task. We evaluate UniXcoder on five code-related tasks over nine datasets. To further evaluate the performance of code fragment representation, we also construct a dataset for a new task, called zero-shot code-to-code search. Results show that our model achieves state-of-the-art performance on most tasks and analysis reveals that comment and AST can both enhance UniXcoder. Copyright © 2022, The Authors. All rights reserved.

关键词： Optimal systems

Revisiting Few-Shot Learning from a Causal Perspective

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lin, Guoliang Xu, Yongheng Lai, Hanjiang Yin, Jian School of Computer Science and Engineering Sun Yat-Sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Artificial Intelligence Sun Yat-Sen University China

Few-shot learning with N-way K-shot scheme is an open challenge in machine learning. Many metric-based approaches have been proposed to tackle this problem, e.g., the Matching Networks and CLIP-Adapter. Despite that these approaches have shown significant progress, the mechanism of why these methods succeed has not been well explored. In this paper, we try to interpret these metric-based few-shot learning methods via causal mechanism. We show that the existing approaches can be viewed as specific forms of front-door adjustment, which can alleviate the effect of spurious correlations and thus learn the causality. This causal interpretation could provide us a new perspective to better understand these existing metric-based methods. Further, based on this causal interpretation, we simply introduce two causal methods for metric-based few-shot learning, which considers not only the relationship between examples but also the diversity of representations. Experimental results demonstrate the superiority of our proposed methods in few-shot classification on various benchmark datasets. Code is available in https://***/lingl1024/causalFewShot. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

A Blockchain-Based Multi-Cloud Storage data Consistency Verification Scheme

学校读者我要写书评

暂无评论

A Blockchain-Based Multi-Cloud Storage Data Consistency Veri...

IEEE International Conference on Big data and Cloud Computing (BdCloud)

作者： Feiyu Wang Jian-tao Zhou Hao Wang Xu Guo College of Computer Science Inner Mongolia University Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Engineering Research Center of Ecological Big Data Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian China

Users worldwide widely use cloud storage because of its efficiency, convenience, and high availability. Multi-cloud storage is usually selected to ensure the high availability of data. Unfortunately, when data is migrated and replicated between multi-cloud data centers, it is not easy to guarantee data con-sistency. This paper proposes an efficient, secure, and new data consistency verification scheme using blockchain technology. In order to reduce the computation and communication overhead in the verification process, our scheme uses encrypted tags to build Merkle hash tree to generate unique and lightweight verification proofs and does not use third-party auditors. The final theoretical and experimental analysis shows that our scheme has higher security and a faster verification process in multi-cloud storage.

关键词： Cloud computing data centers Costs Blockchains Behavioral sciences