检索结果-内蒙古大学图书馆

Self-regulated learning for egocentric video activity anticipation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qi, Zhaobo Wang, Shuhui Su, Chi Su, Li Huang, Qingming Tian, Qi The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518066 China Kingsoft Cloud Beijing100085 China Cloud BU Huawei Technologies Shenzhen518129 China

Future activity anticipation is a challenging problem in egocentric vision. As a standard future activity anticipation paradigm, recursive sequence prediction suffers from the accumulation of errors. To address this problem, we propose a simple and effective Self-Regulated Learning framework, which aims to regulate the intermediate representation consecutively to produce representation that (a) emphasizes the novel information in the frame of the current time-stamp in contrast to previously observed content, and (b) reflects its correlation with previously observed frames. The former is achieved by minimizing a contrastive loss, and the latter can be achieved by a dynamic reweighing mechanism to attend to informative frames in the observed content with a similarity comparison between feature of the current frame and observed frames. The learned final video representation can be further enhanced by multi-task learning which performs joint feature learning on the target activity lab.ls and the automatically detected action and object class tokens. SRL sharply outperforms existing state-of-the-art in most cases on two egocentric video datasets and two third-person video datasets. Its effectiveness is also verified by the experimental fact that the action and object concepts that support the activity semantics can be accurately identified. © 2021, CC BY.

关键词： Semantics

Meta Ordinal Weighting Net For Improving Lung Nodule Classification

学校读者我要写书评

暂无评论

Meta Ordinal Weighting Net For Improving Lung Nodule Classif...

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Yiming Lei Hongming Shan Junping Zhang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Institute of Science and Technology for Brain-inspired Intelligence and MOE Frontiers Center for Brain Science Fudan University Shanghai China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai China

The progression of lung cancer implies the intrinsic ordinal relationship of lung nodules at different stages-from benign to unsure then to malignant. This problem can be solved by ordinal regression methods, which is between classification and regression due to its ordinal lab.l. However, existing convolutional neural network-based ordinal regression methods only focus on modifying classification head based on a randomly sampled mini-batch of data, ignoring the ordinal relationship resided in the data itself. In this paper, we propose a Meta Ordinal Weighting Network (MOW-Net) to explicitly align each training sample with a meta ordinal set (MOS) containing a few samples from all classes. During the training process, the MOW-Net learns a mapping from samples in MOS to corresponding class-specific weight. We further propose a meta cross-entropy loss to optimize the network in a meta-learning scheme. Experimental results demonstrate that the MOW-Net achieves better accuracy than the state-of-the-art ordinal regression methods, especially for the unsure class.

关键词： Training Conferences Lung Lung cancer Data visualization Signal processing Acoustics

Optimizing biomedical ontology alignment in lexical vector space

学校读者我要写书评

暂无评论

Optimizing biomedical ontology alignment in lexical vector s...

作者： Xue, Xingsi Wu, Xiaojing Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology Fuzhou Fujian Minhou China College of Information Science and Engineering Fujian University of Technology Fuzhou Fujian Minhou China Intelligent Information Processing Research Center Fujian University of Technology Fuzhou Fujian Minhou China Institute of Artificial Intelligence Fujian University of Technology Fuzhou Fujian Minhou China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou Fujian Minhou China

Biomedical ontology matching dedicates to find two heterogeneous ontologies' alignment and address their heterogeneity problem. Typically, a biomedical ontology has various biomedical concepts that are described with various lab.ls and datatype property names, which forms a lexical space where each lab.l or datatype property represents one dimension. Therefore, it is an effective way to present two biomedical concepts in a vector space, and use the cosine distance to measure their similarity. In this work, we present two biomedical concepts in a lexical vector space which is constructed with their inner and context concepts' lexical information, and then utilize two vector's cosine distance to measure similarity value. Then, we propose a compact Evolutionary Algorithm (cEA) to find the concept correspondences. The experiment uses Ontology Alignment Evaluation Initiative (OAEI)'s testing cases, and the expeirmental results with Vector space Based Ontology Matcher (VBOM), Genetic Algorithm based Ontology Matcher (GAOM) and OAEI's participants show the effectiveness of our proposal. © 2020 - IOS Press and the authors. All rights reserved.

关键词： Vector spaces

Group-wise inhibition based feature regularization for robust classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Haozhe Wu, Haoqian Xie, Weicheng Liu, Feng Shen, Linlin 1Computer Vision Institute College of Computer Science and Software Engineering 2SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society 3National Engineering Laboratory for Big Data System Computing Technology 4Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen 518060 China

The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e.g. corrupted and adversarial samples). One of the possible reasons is that CNN pays more attention to the most discriminative regions, but ignores the auxiliary features when learning, leading to the lack of feature diversity for final judgment. In our method, we propose to dynamically suppress significant activation values of CNN by group-wise inhibition, but not fixedly or randomly handle them when training. The feature maps with different activation distribution are then processed separately to take the feature independence into account. CNN is finally guided to learn richer discriminative features hierarchically for robust classification according to the proposed regularization. Our method is comprehensively evaluated under multiple settings, including classification against corruptions, adversarial attacks and low data regime. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both robustness and generalization performances, when compared with the state-of-the-art methods. Code is availab.e at https://***/LinusWu/TENET_Training. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolutional neural networks

Spectral2Spectral: Image-spectral Similarity Assisted Deep Spectral CT Reconstruction without Reference

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Guo, Xiaodong Li, Yonghui Chang, Dingyue He, Peng Feng, Peng Yu, Hengyong Wu, Weiwen The Key Lab of Optoelectronic Technology and Systems of the Education Ministry of China Chongqing University Chongqing China The China Academy of Engineering Physics Institute of Materials Mianyang China The Department of Electrical and Computer Engineering University of Massachusetts Lowell LowellMA01854 United States The School of Biomedical Engineering Sun Yat-Sen University Guangdong Shenzhen China The Henan Key Laboratory of Imaging and Intelligent Processing PLA Strategic Support Force Information Engineering University Zhengzhou China

Spectral computed tomography based on a photon-counting detector (PCD) attracts more and more attentions since it has the capability to provide more accurate identification and quantitative analysis for biomedical materials. The limited number of photons within narrow energy bins leads to imaging results of low signal-noise ratio. The existing supervised deep reconstruction networks for CT reconstruction are difficult to address these challenges because it is usually impossible to acquire noise-free clinical images with clear structures as references. In this paper, we propose an iterative deep reconstruction network to synergize unsupervised method and data priors into a unified framework, named as Spectral2Spectral. Our Spectral2Spectral employs an unsupervised deep training strategy to obtain high-quality images from noisy data in an end-to-end fashion. The structural similarity prior within image-spectral domain is refined as a regularization term to further constrain the network training. The weights of neural network are automatically updated to capture image features and structures within the iterative process. Three large-scale preclinical datasets experiments demonstrate that the Spectral2spectral reconstructs better image quality than other the state-of-the-art methods. © 2022, CC0.

关键词： Image reconstruction

Contrastive Learning for Robust Android Malware Familial Classification

学校读者我要写书评

暂无评论

arXiv 2021年

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 Wuhan430074 China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China University of Texas at Dallas Dallas United States 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 Wuhan430074 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. © 2021, CC0.

关键词： Android (operating system)

GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bian, Junyi Huang, Xiaodi Zhou, Hong Zhu, Shanfeng School of Computer Science Fudan University Shanghai200433 China School of Computing and Mathematics Charles Sturt University AlburyNSW2640 Australia Atypon Systems LLC United Kingdom Institute of Science and Technology for Brain-Inspired Intelligence Fudan University China Ministry of Education Shanghai200433 China MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China Zhangjiang Fudan International Innovation Center Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai200433 China

Extracting summaries from long documents can be regarded as sentence classification using the structural information of the documents. How to use such structural information to summarize a document is challenging. In this paper, we propose GoSum, a novel graph and reinforcement learning based extractive model for long-paper summarization. In particular, GoSum encodes sentence states in reinforcement learning by building a heterogeneous graph for each input document at different discourse levels. An edge in the graph reflects the discourse hierarchy of a document for restraining the semantic drifts across section boundaries. We evaluate GoSum on two datasets of scientific articles summarization: PubMed and arXiv. The experimental results have demonstrated that GoSum achieve state-of-the-art results compared with strong baselines of both extractive and abstractive models. The ablation studies further validate that the performance of our GoSum benefits from the use of discourse information. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

Compose Like Humans: Jointly Improving the Coherence and Novelty for Modern Chinese Poetry Generation

学校读者我要写书评

暂无评论

Compose Like Humans: Jointly Improving the Coherence and Nov...

International Joint Conference on Neural Networks (IJCNN)

作者： Lei Shen Xiaoyu Guo Meng Chen Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China JD AI Beijing China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

Chinese poetry is an important part of worldwide culture, and classical and modern sub-branches are quite different. The former is a unique genre and has strict constraints, while the latter is very flexible in length, optional to have rhymes, and similar to modern poetry in other languages. Thus, it requires more to control the coherence and improve the novelty. In this paper, we propose a generate-retrieve-then-refine paradigm to jointly improve the coherence and novelty. In the first stage, a draft is generated given keywords (i.e., topics) only. The second stage produces a "refining vector" from retrieval lines. At last, we take into consideration both the draft and the "refining vector" to generate a new poem. The draft provides future sentence-level information for a line to be generated. Meanwhile, the "refining vector" points out the direction of refinement based on impressive words detection mechanism which can learn good patterns from references and then create new ones via insertion operation. Experimental results on a collected large-scale modern Chinese poetry dataset show that our proposed approach can not only generate more coherent poems, but also improve the diversity and novelty.

关键词： Coherence Decoding Feeds Writing History Recurrent neural networks Prototypes

Compose Like Humans: Jointly Improving the Coherence and Novelty for Modern Chinese Poetry Generation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shen, Lei Guo, Xiaoyu Chen, Meng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China JD AI Beijing China

关键词： Refining