检索结果-内蒙古大学图书馆

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

来源：评论

学校读者我要写书评

暂无评论

Learning Music-Dance Representations through Explicit-Implicit Rhythm Synchronization

arXiv

引用

arXiv 2022年

作者： Yu, Jiashuo Pu, Junfu Cheng, Ying Feng, Rui Shan, Ying The School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai200438 China The Academy for Engineering and Technology Fudan University Shanghai200438 China The Applied Research Center PCG Tencent Shenzhen518000 China

Although audio-visual representation has been proven to be applicable in many downstream tasks, the representation of dancing videos, which is more specific and always accompanied by music with complex auditory contents, remains challenging and uninvestigated. Considering the intrinsic alignment between the cadent movement of the dancer and music rhythm, we introduce MuDaR, a novel Music-Dance Representation learning framework to perform the synchronization of music and dance rhythms both in explicit and implicit ways. Specifically, we derive the dance rhythms based on visual appearance and motion cues inspired by the music rhythm analysis. Then the visual rhythms are temporally aligned with the music counterparts, which are extracted by the amplitude of sound intensity. Meanwhile, we exploit the implicit coherence of rhythms implied in audio and visual streams by contrastive learning. The model learns the joint embedding by predicting the temporal consistency between audio-visual pairs. The music-dance representation, together with the capability of detecting audio and visual rhythms, can further be applied to three downstream tasks: (a) dance classification, (b) music-dance retrieval, and (c) music-dance retargeting. Extensive experiments demonstrate that our proposed framework outperforms other self-supervised methods by a large margin. © 2022, CC BY.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework

arXiv

引用

arXiv 2023年

作者： Dai, Siran Xu, Qianqian Yang, Zhiyong Cao, Xiaochun Huang, Qingming SKLOIS 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 Tech. CAS China School of Computer Science and Tech. 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

The Area Under the ROC Curve (AUC) is a widely employed metric in long-tailed classification scenarios. Nevertheless, most existing methods primarily assume that training and testing examples are drawn i.i.d. from the same distribution, which is often unachievable in practice. Distributionally Robust Optimization (DRO) enhances model performance by optimizing it for the local worst-case scenario, but directly integrating AUC optimization with DRO results in an intractable optimization problem. To tackle this challenge, methodically we propose an instance-wise surrogate loss of Distributionally Robust AUC (DRAUC) and build our optimization framework on top of it. Moreover, we highlight that conventional DRAUC may induce lab.l bias, hence introducing distribution-aware DRAUC as a more suitable metric for robust AUC learning. Theoretically, we affirm that the generalization gap between the training loss and testing error diminishes if the training set is sufficiently large. Empirically, experiments on corrupted benchmark datasets demonstrate the effectiveness of our proposed method. Code is availab.e at: https://***/EldercatSAM/DRAUC. © 2023, CC BY.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Robust Android Malware Familial Classification

引用

IEEE Transactions on Dependable and Secure computing 2022年 1-14页

作者： Wu, Yueming Dou, Shihan Zou, Deqing Yang, Wei Qiang, Weizhong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China University of Texas at Dallas Dallas USA National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Due to its open-source nature, Android operating system has been the main target of attackers to exploit. Malware creators always perform different code obfuscations on their apps to hide malicious activities. Features extracted from these obfuscated samples through program analysis contain many useless and disguised features, which leads to many false negatives. To address the issue, in this paper, we demonstrate that obfuscation-resilient malware family analysis can be achieved through contrastive learning. The key insight behind our analysis is that contrastive learning can be used to reduce the difference introduced by obfuscation while amplifying the difference between malware and other types of malware. Based on the proposed analysis, we design a system that can achieve robust and interpretable classification of Android malware. To achieve robust classification, we perform contrastive learning on malware samples to learn an encoder that can automatically extract robust features from malware samples. To achieve interpretable classification, we transform the function call graph of a sample into an image by centrality analysis. Then the corresponding heatmaps can be obtained by visualization techniques. These heatmaps can help users understand why the malware is classified as this family. We implement IFDroid and perform extensive evaluations on two datasets. Experimental results show that IFDroid is superior to state-of-the-art Android malware familial classification systems. Moreover, IFDroid is capable of maintaining a 98.4% F1 on classifying 69,421 obfuscated malware samples. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning

arXiv

引用

arXiv 2023年

作者： Wang, Zitai Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming SKLOIS 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 Tech. CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Alibaba Group China School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University China BDKM University of Chinese Academy of Sciences China

Real-world datasets are typically imbalanced in the sense that only a few classes have numerous samples, while many classes are associated with only a few samples. As a result, a naïve ERM learning process will be biased towards the majority classes, making it difficult to generalize to the minority classes. To address this issue, one simple but effective approach is to modify the loss function to emphasize the learning on minority classes, such as re-weighting the losses or adjusting the logits via class-dependent terms. However, existing generalization analysis of such losses is still coarse-grained and fragmented, failing to explain some empirical results. To bridge this gap, we propose a novel technique named data-dependent contraction to capture how these modified losses handle different classes. On top of this technique, a fine-grained generalization bound is established for imbalanced learning, which helps reveal the mystery of re-weighting and logit-adjustment in a unified manner. Furthermore, a principled learning algorithm is developed based on the theoretical insights. Finally, the empirical results on benchmark datasets not only validate the theoretical results but also demonstrate the effectiveness of the proposed method. © 2023, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

In-situ synthesized SiC/TiC/SiTiOC hybrid nanofiber mats for broad-range temperature microwave absorption

引用

Science China Technological Sciences 2025年第6期 183-196页

作者： Yashan HUO Yuetong QIAN Minshan ZHAO Lei ZHANG Yujia TAN Zhihui HE Peng MIAO Fuchun ZHANG Wei CUI Renchao CHE School of Physics and Electronic Information Yan'an University Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Laboratory of Advanced Materials Shanghai Key Lab of Molecular Catalysis and Innovative Materials Academy for Engineering &Technology Advanced Coatings Research Center of Ministry of Education of China Fudan University School of Materials and Chemical Engineering Xi'an Technological University School of Materials Science & Engineering Tongji University College of Physics Donghua University

Efficient, temperature-insensitive electromagnetic attenuation materials are critical for high microwave absorption at high temperatures. This study presents SiC/TiC/SiTiOC hybrid nanofiber mats constructed using an in-situ synthesis method;these mats incorporate SiC/TiC as the microwave loss unit and SiTiOC as the antioxidant unit, offering an innovative approach to high-temperature microwave absorption. The introduction of high-conductivity TiC not only optimizes the dielectric constant and impedance matching of the material but also enhances its thermal cycling stability. This design ensures steady electromagnetic attenuation, enabling the hybrid nanofiber mats to maintain robust absorption performance in the X-band, even at high temperatures. At 873 K, the material demonstrates an effective absorption bandwidth of 3.6 GHz and a minimum reflection loss of-45.55 dB. Compared to single-system absorbers, such as SiC/C nanofiber materials, with a single system, the multicomponent SiC/TiC/SiTiOC hybrid nanofiber mats deliver reliable absorption performance in the temperature range of 293–873 K. This study confirms that highly conductive titanium-based ceramic materials used for dielectric property regulation effectively address the challenges of poor temperature stability and limited reusability in high-temperature carbon-ceramic absorbing materials, providing valuable insights and guidance for designing efficient microwave absorbers that can operate across a wide temperature range.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LightXML: Transformer with dynamic negative sampling for high-performance extreme multi-lab.l text classification

arXiv

引用

arXiv 2021年

作者： Jiang, Ting Wang, Deqing Sun, Leilei Yang, Huayi Zhao, Zhengyang Zhuang, Fuzhen SKLSDE and BDBC Lab Beihang University Beijing China Key Lab of Intelligent Information Processing of CAS Institute of Computing Technology CAS Beijing China Beijing Advanced Innovation Center for Imaging Theory and Technology Academy for Multidisciplinary Studies Capital Normal University Beijing China

Extreme Multi-lab.l text Classification (XMC) is a task of finding the most relevant lab.ls from a large lab.l set. Nowadays deep learning-based methods have shown significant success in XMC. However, the existing methods (e.g., AttentionXML and X-Transformer etc) still suffer from 1) combining several models to train and predict for one dataset, and 2) sampling negative lab.ls statically during the process of training lab.l ranking model, which reduces both the efficiency and accuracy of the model. To address the above problems, we proposed LightXML, which adopts end-to-end training and dynamic negative lab.ls sampling. In LightXML, we use generative cooperative networks to recall and rank lab.ls, in which lab.l recalling part generates negative and positive lab.ls, and lab.l ranking part distinguishes positive lab.ls from these lab.ls. Through these networks, negative lab.ls are sampled dynamically during lab.l ranking part training by feeding with the same text representation. Extensive experiments show that LightXML outperforms state-of-the-art methods in five extreme multi-lab.l datasets with much smaller model size and lower computational complexity. In particular, on the Amazon dataset with 670K lab.ls, LightXML can reduce the model size up to 72% compared to AttentionXML. Our code is availab.e at http://***/kongds/LightXML. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

The Minority Matters: A Diversity-Promoting Collab.rative Metric Learning Algorithm

arXiv

引用

arXiv 2022年

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

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 term 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. © 2022, CC BY-NC-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Iterative network pruning with uncertainty regularization for lifelong sentiment classification

arXiv

引用

arXiv 2021年

作者： Geng, Binzong Yang, Min Yuan, Fajie Wang, Shupeng Ao, Xiang Xu, Ruifeng University of Science and Technology of China China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Westlake University Key Lab of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology CAS Harbin Institute of Technology Shenzhen China Tencent

Lifelong learning capabilities are crucial for sentiment classifiers to process continuous streams of opinioned information on the Web. However, performing lifelong learning is non-trivial for deep neural networks as continually training of incrementally availab.e information inevitably results in catastrophic forgetting or interference. In this paper, we propose a novel iterative network pruning with uncertainty regularization method for lifelong sentiment classification (IPRLS), which leverages the principles of network pruning and weight regularization. By performing network pruning with uncertainty regularization in an iterative manner, IPRLS can adapt a single BERT model to work with continuously arriving data from multiple domains while avoiding catastrophic forgetting and interference. Specifically, we leverage an iterative pruning method to remove redundant parameters in large deep networks so that the freed-up space can then be employed to learn new tasks, tackling the catastrophic forgetting problem. Instead of keeping the old-tasks fixed when learning new tasks, we also use an uncertainty regularization based on the Bayesian online learning framework to constrain the update of old tasks weights in BERT, which enables positive backward transfer, i.e. learning new tasks improves performance on past tasks while protecting old knowledge from being lost. In addition, we propose a task-specific low-dimensional residual function in parallel to each layer of BERT, which makes IPRLS less prone to losing the knowledge saved in the base BERT network when learning a new task. Extensive experiments on 16 popular review corpora demonstrate that the proposed IPRLS method significantly outperforms the strong baselines for lifelong sentiment classification. For reproducibility, we submit the code and data at: https://***/siat-nlp/IPRLS. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Global-Local Attention Network for Semantic Segmentation in Aerial Images

Global-Local Attention Network for Semantic Segmentation in ...

引用

International Conference on Pattern Recognition

作者： Minglong Li Lianlei Shan Xiaobin Li Yang Bai Dengji Zhou Weiqiang Wang Ke Lv Bin Luo Si-Bao Chen University of Chinese Academy of Sciences Beijing China Aerospace Information Research Institute Chinese Academy of Science Beijing China MOE Key Lab of Signal Processing and Intelligent Computing School of Computer Science and Technology Anhui University Hefei China

Errors in semantic segmentation could be classified into two types: the large area misclassification and inaccurate local boundaries. Previously attention-based methods typically capture rich global contextual information, which benefits the large area classification but cannot address the local errors of boundaries. In this paper, we propose a Global-Local Attention Network (GLANet) which can simultaneously consider the global context and local details. Specifically, our GLANet consists of two branches: (1) the global attention branch and (2) local attention branch. Furthermore, three different modules are embedded in GLANet for respectively modelling the semantic interdependencies in spatial, channel and boundary dimension. Lastly, we merge the outputs of different branches to enhance the feature representation further, resulting in more precise segmentation. Overall, the proposed method achieves the competitive segmentation accuracy on two public aerial image datasets, bringing significant improvements over the existing baselines.

关键词： Image segmentation Image color analysis Image edge detection Semantics Vegetation mapping Vegetation Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：