检索结果-内蒙古大学图书馆

BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lin, Jiatai Han, Guoqiang Xu, Xuemiao Liang, Changhong Wong, Tien-Tsin Chen, C.L. Philip Liu, Zaiyi Han, Chu The School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Southern Medical University Guangzhou510080 China School of Computer Science and Engineering South China University of Technology State Key Laboratory of Subtropical Building Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

Class activation mapping (CAM), a visualization technique for interpreting deep learning models, is now commonly used for weakly supervised semantic segmentation (WSSS) and object localization (WSOL). It is the weighted aggregation of the feature maps by activating the high class-relevance ones. Current CAM methods achieve it relying on the training outcomes, such as predicted scores (forward information), gradients (backward information), etc. However, when with small-scale data, unstable training may lead to less effective model outcomes and generate unreliable weights, finally resulting in incorrect activation and noisy CAM seeds. In this paper, we propose an outcome-agnostic CAM approach, called BroadCAM, for small-scale weakly supervised applications. Since broad learning system (BLS) is independent to the model learning, BroadCAM can avoid the weights being affected by the unreliable model outcomes when with small-scale data. By evaluating BroadCAM on VOC2012 (natural images) and BCSS-WSSS (medical images) for WSSS and OpenImages30k for WSOL, BroadCAM demonstrates superior performance than existing CAM methods with small-scale data (less than 5%) in different CNN architectures. It also achieves SOTA performance with large-scale training data. Extensive qualitative comparisons are conducted to demonstrate how BroadCAM activates the high class-relevance feature maps and generates reliable CAMs when with small-scale training data. © 2023, CC BY.

关键词： Learning systems

Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Leng, Yicheng Fang, Chaowei Li, Gen Fang, Yixiang Li, Guanbin School of Artificial Intelligence Xidian University Xi’an China School of Data Science The Chinese University of Hong Kong Shenzhen China Afirstsoft Shenzhen China School of Computer Science and Engineering Research Institute of Sun Yat-sen University in Shenzhen Sun Yat-sen University Guangzhou China GuangDong Province Key Laboratory of Information Security Technology China

Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing. Visible watermark removal aims to eliminate the interference of watermarks and restore the background content. However, existing methods often implement watermark component removal and background restoration tasks within a singular branch, leading to residual watermarks in the predictions and ignoring cases where watermarks heavily obscure the background. To address these limitations, this study introduces the Removing Interference and Recovering Content Imaginatively (RIRCI) framework. RIRCI embodies a two-stage approach: the initial phase centers on discerning and segregating the watermark component, while the subsequent phase focuses on background content restoration. To achieve meticulous background restoration, our proposed model employs a dual-path network capable of fully exploring the intrinsic background information beneath semi-transparent watermarks and peripheral contextual information from unaffected regions. Moreover, a Global and Local Context Interaction module is built upon multi-layer perceptrons and bidirectional feature transformation for comprehensive representation modeling in the background restoration phase. The efficacy of our approach is empirically validated across two large-scale datasets, and our findings reveal a marked enhancement over existing watermark removal techniques. Copyright © 2023, The Authors. All rights reserved.

关键词： Restoration

Twisted-pair superposition transmission

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cai, Suihua Ma, Xiao School of Data and Computer Science Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China

We propose in this paper a new coding scheme called twisted-pair superposition transmission (TPST). The encoding is to "mix together" a pair of basic codes by superposition, while the decoding can be implemented as a successive cancellation list decoding algorithm. The most significant features of the TPST code are its predictable performance that can be estimated numerically from the basic codes and its flexible construction in the sense that it can be easily adapted to different coding rates. To construct good TPST codes in the finite length regime, we propose two design approaches – rate allocation and partial superposition. By taking tail-biting convolutional codes (TBCC) as basic codes, we show by numerical results that the TPST codes can have near-capacity performance in the short length regime. Copyright © 2021, The Authors. All rights reserved.

关键词： Decoding

Adaptive Perception for Unified Visual Multi-modal Object Tracking

学校读者我要写书评

暂无评论

IEEE Transactions on Artificial Intelligence

IEEE Transactions on Artificial Intelligence 2025年

作者： Hu, Xiantao Zhong, Bineng Liang, Qihua Shi, Liangtao Mo, Zhiyi Tai, Ying Yang, Jian Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining Guilin541004 China Guangxi Normal University Security Guilin541004 China Guangxi Normal University Intelligent Technology Guilin541004 China Guangxi Normal University Ministry of Education Guilin541004 China Wuzhou University School of Data Science Wuzhou543002 China Wuzhou University Software Engineering Wuzhou543002 China Nanjing University State Key Laboratory for Novel Software Technology Suzhou215163 China Nanjing University of Science and Technology School of Computer Science Nanjing210094 China Nanjing University of Science and Technology Engineering Nanjing210094 China

Recently, many multi-modal trackers prioritize RGB as the dominant modality, treating other modalities as auxiliary, and fine-tuning separately various multi-modal tasks. This imbalance in modality dependence limits the ability of methods to dynamically utilize complementary information from each modality in complex scenarios, making it challenging to fully perceive the advantages of multi-modal. As a result, a unified parameter model often underperforms in various multi-modal tracking tasks. To address this issue, we propose APTrack, a novel unified tracker designed for multi-modal adaptive perception. Unlike previous methods, APTrack explores a unified representation through an equal modeling strategy. This strategy allows the model to dynamically adapt to various modalities and tasks without requiring additional fine-tuning between different tasks. Moreover, our tracker integrates an adaptive modality interaction (AMI) module that efficiently bridges cross-modality interactions by generating learnable tokens. Experiments conducted on five diverse multi-modal datasets (RGBT234, LasHeR, VisEvent, DepthTrack, and VOT-RGBD2022) demonstrate that APTrack not only surpasses existing state-of-the-art unified multi-modal trackers but also outperforms trackers designed for specific multi-modal tasks. © 2020 IEEE.

关键词： Multicarrier modulation

CRS-Diff: Controllab.e Remote Sensing Image Generation with Diffusion Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, datao Cao, Xiangyong Hou, Xingsong Jiang, Zhongyuan Liu, Junmin Meng, Deyu The School of Computer Science and Technology the Ministry of Education Key Lab for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China The School of Information and Communications Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China The School of Cyber Engineering Xidian University Shaanxi Xi’an710049 China The School of Mathematics and Statistics the Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Shaanxi Xi’an710049 China Guangdong Guangzhou510555 China

The emergence of generative models has revolutionized the field of remote sensing (RS) image generation. Despite generating high-quality images, existing methods are limited in relying mainly on text control conditions, and thus do not always generate images accurately and stably. In this paper, we propose CRS-Diff, a new RS generative framework specifically tailored for RS image generation, leveraging the inherent advantages of diffusion models while integrating more advanced control mechanisms. Specifically, CRS-Diff can simultaneously support text-condition, metadata-condition, and image-condition control inputs, thus enabling more precise control to refine the generation process. To effectively integrate multiple condition control information, we introduce a new conditional control mechanism to achieve multi-scale feature fusion, thus enhancing the guiding effect of control conditions. To our knowledge, CRS-Diff is the first multiple-condition controllab.e RS generative model. Experimental results in single-condition and multiple-condition cases have demonstrated the superior ability of our CRS-Diff to generate RS images both quantitatively and qualitatively compared with previous methods. Additionally, our CRS-Diff can serve as a data engine that generates high-quality training data for downstream tasks, e.g., road extraction. The code is availab.e at https://***/Sonettoo/CRS-Diff. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. The School of Information Technology Jiangxi University of Finance and Economics Nanchang330013 China The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Lab. School of Electrical and Electronic Engineering Nanyang Technology University Singapore The Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The China-Singapore International Joint Research Institute Singapore

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. One possible reason is that fully fine-tuned ViT-based models may disrupt the pre-trained features [1], [2] and overfit to some data-specific patterns [3]. To alleviate this issue, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. The code and trained model have been released at: https://***/LoveSiameseCat/FAViT. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

Example-based web page recoloring method

学校读者我要写书评

暂无评论

Frontiers of computer science 2020年第5期14卷 229-231页

作者： Yonghao Long Zhihao Zang Xiangping Chen Fan Zhou Xiaonan Luo School of Data and Computer Science National Engineering Research Center of Digital LifeSun Yat-sen UniversityGuangzhou510006China Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion The School of Communication and DesignSun Yat-sen UniversityGuangzhou510006China School of Computer Science and Information Security Guilin University of Electronic TechnologyGuilin541004China

1 Introduction The user interface(UI)is very important for a software product,and a well-designed UI will attract users and make a good *** has been shown that color plays an important role in invoking emotional reactions[1],influencing usability[2],forming first impressions[3],and affecting the energy cost of the UI[4].Generating satisfying color schemes has high requirements for experience,aesthetic,and creative inspiration of designers[5].

关键词： web coloring satisfying

Joint Transmit Precoding and Rate Allocation for Rate-Splitting Multiple Access Based Wireless Backhaul HetNets

学校读者我要写书评

暂无评论

Joint Transmit Precoding and Rate Allocation for Rate-Splitt...

IEEE International Conference on Communications (ICC)

作者： Guangyuan Zheng Miaowen Wen Yingyang Chen Yik-Chung Wu H. Vincent Poor School of Electronic and Information Engineering South China University of Technology Guangzhou China College of Information Science and Technology Jinan University Guangzhou China Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Jinan University Guangzhou China Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Department of Electrical and Computer Engineering Princeton University Princeton NJ USA

In this paper, we investigate the application of rate-splitting multiple access (RSMA) in a two-tier wireless backhaul heterogeneous network (HetNet), where a macro base station (MBS) simultaneously transmits wireless access signals to macro-cell users (MCUs) and wireless backhaul signals to small base stations (SBSs) by leveraging RSMA. In order to improve the system spectral efficiency (SE) while guaranteeing the quality-of-service (QoS) of each user, we formulate an optimization problem to maximize the sum SE by jointly considering transmit precoding and rate allocation at the MBS and SBSs. To solve the formulated non-convex problem, we propose an iterative algorithm based on successive convex approximation (SCA). Simulation results show that the application of RSMA can achieve higher SE over conventional non-orthogonal multiple access (NOMA) and space division multiple access (SDMA) under different network loads. In addition, RSMA has better flexibility than other benchmark schemes in meeting the increasing QoS requirements of users.

关键词：

Privacy-aware OrLa based access control model in the cloud 32

学校读者我要写书评

暂无评论

Privacy-aware OrLa based access control model in the cloud

32nd International Conference on Software Engineering and Knowledge Engineering, SEKE 2020

作者： Shao, Pengfei Jin, Shuyuan School of Data and Computer Science Sun Yat-sen University Guangzhou China GuangDong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou China

ISBN: (纸本)1891706500

In recent years, cloud computing has been widely adopted by an increasing number of enterprises and individuals because of its attractive features, such as its large scale, low costs, and pay-per-use. Nevertheless, traditional access control models cannot satisfy the security requirements of complex cloud environments. In this paper, a privacy-aware access control model (Pa-Orlab.C) is proposed that emphasizes privacy protection and flexibility. This model combines Organization based Access Control (OrBAC) model with lab.l-based access control (lab.C) model and retains their respective advantages, making it more suitable for the cloud. By introducing the concept of purpose, the issue of lacking privacy protection is well addressed and the problem of the separation of control and ownership is alleviated to some extent. In order to get a more precise access purpose, two methods (static declaration and dynamic acquisition) and a negotiation module are also applied in this model. Finally, we illustrate the use of Pa-Orlab.C with a case study and summarize this model. © 2020 Knowledge Systems Institute Graduate school. All rights reserved.

关键词： Access control models