检索结果-内蒙古大学图书馆

VideoLT: Large-scale long-tailed video recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Xing Wu, Zuxuan Weng, Zejia Fu, Huazhu Chen, Jingjing Jiang, Yu-Gang Davis, Larry Academy for Engineering and Technology Fudan University Shanghai Key Lab of Intel. Info. Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing Inception Institute of Artificial Intelligence University of Maryland

label distributions in real-world are oftentimes long-tailed and imbalanced, resulting in biased models towards dominant labels. While long-tailed recognition has been extensively studied for image classification tasks, limited effort has been made for the video domain. In this paper, we introduce VideoLT, a large-scale long-tailed video recognition dataset, as a step toward real-world video recognition. VideoLT contains 256,218 untrimmed videos, annotated into 1,004 classes with a long-tailed distribution. Through extensive studies, we demonstrate that state-of-the-art methods used for long-tailed image recognition do not perform well in the video domain due to the additional temporal dimension in videos. This motivates us to propose FrameStack, a simple yet effective method for long-tailed video recognition. In particular, FrameStack performs sampling at the frame-level in order to balance class distributions, and the sampling ratio is dynamically determined using knowledge derived from the network during training. Experimental results demonstrate that FrameStack can improve classification performance without sacrificing the overall accuracy. Code and dataset are available at: https://***/17Skye17/VideoLT. Copyright © 2021, The Authors. All rights reserved.

关键词： Image recognition

Hard instance learning for quantum adiabatic prime factorization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lin, Jian Zhang, Zhengfeng Zhang, Junping Li, Xiaopeng State Key Laboratory of Surface Physics Institute of Nanoelectronics and Quantum Computing Department of Physics Fudan University Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Shanghai Qi Zhi Institute AI Tower Xuhui District Shanghai200232 China

Prime factorization is a difficult problem with classical computing, whose exponential hardness is the foundation of Rivest-Shamir-Adleman (RSA) cryptography. With programmable quantum devices, adiabatic quantum computing has been proposed as a plausible approach to solve prime factorization, having promising advantage over classical computing. Here, we find there are certain hard instances that are consistently intractable for both classical simulated annealing and un-configured adiabatic quantum computing (AQC). Aiming at an automated architecture for optimal configuration of quantum adiabatic factorization, we apply a deep reinforcement learning (RL) method to configure the AQC algorithm. By setting the success probability of the worst-case problem instances as the reward to RL, we show the AQC performance on the hard instances is dramatically improved by RL configuration. The success probability also becomes more evenly distributed over different problem instances, meaning the configured AQC is more stable as compared to the un-configured case. Through a technique of transfer learning, we find prominent evidence that the framework of AQC configuration is scalable—the configured AQC as trained on five qubits remains working efficiently on nine qubits with a minimal amount of additional training cost. Copyright © 2021, The Authors. All rights reserved.

关键词： Factorization

OpenAUC: Towards AUC-Oriented Open-Set Recognition

学校读者我要写书评

暂无评论

arXiv 2022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. Sun Yat-sen University Shenzhen Campus China BDKM University of Chinese Academy of Sciences China Peng Cheng Laboratory China

Traditional machine learning follows a close-set assumption that the training and test set share the same label space. While in many practical scenarios, it is inevitable that some test samples belong to unknown classes (open-set). To fix this issue, Open-Set Recognition (OSR), whose goal is to make correct predictions on both close-set samples and open-set samples, has attracted rising attention. In this direction, the vast majority of literature focuses on the pattern of open-set samples. However, how to evaluate model performance in this challenging task is still unsolved. In this paper, a systematic analysis reveals that most existing metrics are essentially inconsistent with the aforementioned goal of OSR: (1) For metrics extended from close-set classification, such as Open-set F-score, Youden’s index, and Normalized Accuracy, a poor open-set prediction can escape from a low performance score with a superior close-set prediction. (2) Novelty detection AUC, which measures the ranking performance between close-set and open-set samples, ignores the close-set performance. To fix these issues, we propose a novel metric named OpenAUC. Compared with existing metrics, OpenAUC enjoys a concise pairwise formulation that evaluates open-set performance and close-set performance in a coupling manner. Further analysis shows that OpenAUC is free from the aforementioned inconsistency properties. Finally, an end-to-end learning method is proposed to minimize the OpenAUC risk, and the experimental results on popular benchmark datasets speak to its effectiveness. Project Page: https://***/wang22ti/OpenAUC. © 2022, CC BY.

关键词： Forecasting

CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shen, Lei Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Emotion-controllable response generation is an attractive and valuable task that aims to make open-domain conversations more empathetic and engaging. Existing methods mainly enhance the emotion expression by adding regularization terms to standard cross-entropy loss and thus influence the training process. However, due to the lack of further consideration of content consistency, the common problem of response generation tasks, safe response, is intensified. Besides, query emotions that can help model the relationship between query and response are simply ignored in previous models, which would further hurt the coherence. To alleviate these problems, we propose a novel framework named Curriculum Dual Learning (CDL) which extends the emotion-controllable response generation to a dual task to generate emotional responses and emotional queries alternatively. CDL utilizes two rewards focusing on emotion and content to improve the duality. Additionally, it applies curriculum learning to gradually generate high-quality responses based on the difficulties of expressing various emotions. Experimental results show that CDL significantly outperforms the baselines in terms of coherence, diversity, and relation to emotion factors. Copyright © 2020, The Authors. All rights reserved.

关键词： Curricula

DMNER: Biomedical Named Entity Recognition by Detection and Matching

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bian, Junyi Jiang, Rongze Zhai, Weiqi Huang, Tianyang Zhou, Hong Zhu, Shanfeng School of Computer Science Fudan University Shanghai200433 China Atypon Systems LLC United Kingdom Institute of Science and Technology for Brain-Inspired Intelligence Fudan University China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University 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

Biomedical named entity recognition (BNER) serves as the foundation for numerous biomedical text mining tasks. Unlike general NER, BNER require a comprehensive grasp of the domain, and incorporating external knowledge beyond training data poses a significant challenge. In this study, we propose a novel BNER framework called DMNER. By leveraging existing entity representation models SAP-BERT, we tackle BNER as a two-step process: entity boundary detection and biomedical entity matching. DMNER exhibits applicability across multiple NER scenarios: 1) In supervised NER, we observe that DMNER effectively rectifies the output of baseline NER models, thereby further enhancing performance. 2) In distantly supervised NER, combining MRC and AutoNER as span boundary detectors enables DMNER to achieve satisfactory results. 3) For training NER by merging multiple datasets, we adopt a framework similar to DS-NER but additionally leverage ChatGPT to obtain high-quality phrases in the training. Through extensive experiments conducted on 10 benchmark datasets, we demonstrate the versatility and effectiveness of DMNER. Copyright © 2023, The Authors. All rights reserved.

关键词： Character recognition

ISIA food-500: A dataset for large-scale food recognition via stacked global-local attention network

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Min, Weiqing Liu, Linhu Wang, Zhiling Luo, Zhengdong Wei, Xiaoming Wei, Xiaolin Jiang, Shuqiang Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Meituan-Dianping Group China

Food recognition has received more and more attention in the multimedia community for its various real-world applications, such as diet management and self-service restaurants. A large-scale ontology of food images is urgently needed for developing advanced large-scale food recognition algorithms, as well as for providing the benchmark dataset for such algorithms. To encourage further progress in food recognition, we introduce the dataset ISIA Food-500 with 500 categories from the list in the Wikipedia and 399,726 images, a more comprehensive food dataset that surpasses existing popular benchmark datasets by category coverage and data volume. Furthermore, we propose a stacked global-local attention network, which consists of two sub-networks for food recognition. One sub-network first utilizes hybrid spatial-channel attention to extract more discriminative features, and then aggregates these multi-scale discriminative features from multiple layers into global-level representation (e.g., texture and shape information about food). The other one generates attentional regions (e.g., ingredient relevant regions) from different regions via cascaded spatial transformers, and further aggregates these multi-scale regional features from different layers into local-level representation. These two types of features are finally fused as comprehensive representation for food recognition. Extensive experiments on ISIA Food-500 and other two popular benchmark datasets demonstrate the effectiveness of our proposed method, and thus can be considered as one strong baseline. The dataset, code and models can be found at http://123.57.42.89/Foodcomputing-Dataset/***. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

Universal deep network for steganalysis of color image based on channel representation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wei, Kangkang Luo, Weiqi Tan, Shunquan Huang, Jiwu The Guangdong Key Lab of Information Security Technology School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Up to now, most existing steganalytic methods are designed for grayscale images, and they are not suitable for color images that are widely used in current social networks. In this paper, we design a universal color image steganalysis network (called UCNet) in spatial and JPEG domains. The proposed method includes preprocessing, convolutional, and classification modules. To preserve the steganographic artifacts in each color channel, in preprocessing module, we firstly separate the input image into three channels according to the corresponding embedding spaces (i.e. RGB for spatial steganography and YCbCr for JPEG steganography), and then extract the image residuals with 62 fixed high-pass filters, finally concatenate all truncated residuals for subsequent analysis rather than adding them together with normal convolution like existing CNN-based steganalyzers. To accelerate the network convergence and effectively reduce the number of parameters, in convolutional module, we carefully design three types of layers with different shortcut connections and group convolution structures to further learn high-level steganalytic features. In classification module, we employ a global average pooling and fully connected layer for classification. We conduct extensive experiments on ALASKA II to demonstrate that the proposed method can achieve state-of-the-art results compared with the modern CNN-based steganalyzers (e.g., SRNet and J-YeNet) in both spatial and JPEG domains, while keeping relatively few memory requirements and training time. Furthermore, we also provide necessary descriptions and many ablation experiments to verify the rationality of the network design. Copyright © 2021, The Authors. All rights reserved.

关键词： Steganography

Automatic diagnosis of disc herniation based on DenseNet fusion model 8

学校读者我要写书评

暂无评论

Automatic diagnosis of disc herniation based on DenseNet fus...

8th International Conference on Digital Home, ICDH 2020

作者： Wang, Zimin Qin, Junyan Huang, Jinrong Wang, Yumeng Li, Ji Guilin University of Electronic Technology Guangxi Colleges and Universities Key Lab. of Intelligent Processing of Computer Image and Graphics Guilin541004 China Guilin Huigu Institute of Artificial Intelligence Industrial Technology Guilin541004 China Guilin University of Electronic Technology School of Computer Science and Information Security Guilin541004 China

ISBN: (纸本)9781728192345

Spine MRI images generally have the characteristics of low contrast and much noise. Because the variable shape of the spine edge, the traditional spine image segmentation method requires a lot of preprocessing and can not perform image segmentation automatically, which is inefficient and cannot compliant the clinical work requirements. So as to solve the above problems, this paper use deep learning algorithms to identify the spine images, and proposed a disc herniation recognition method for spinal MRI images which based on DenseNet fusion model. Use DenseNet and Inception-Resnet-V2 model fusion to get more image features and improve the image recognition accuracy. Experiments prove that this method can be used to identify the herniation of spinal intervertebral disc with high accuracy and real-time. © 2020 IEEE.

关键词： Image segmentation

Drug3D-DTI: Improved Drug-target Interaction Prediction by Incorporating Spatial information of Small Molecules

学校读者我要写书评

暂无评论

Drug3D-DTI: Improved Drug-target Interaction Prediction by I...

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Liao, Zhirui Huang, Xiaodi Mamitsuka, Hiroshi Zhu, Shanfeng Fudan University School of Computer Science Shanghai200433 China Institute of Artificial Intelligence Biomedicine Nanjing University Nanjing China School of Computing Mathematics and Engineering Charles Sturt University AlburyNSW2640 Australia Bioinformatics Center Institute for Chemical Research Kyoto University Kyoto Uji611-0011 Japan Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai200433 China Ministry of Education 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

ISBN: (纸本)9781665401265

A number of machine learning (ML) approaches for drug discovery have been available that rely only on sequential (1D) and planar (2D) information without effectively using the 3D information for generating features of drugs. However, 3D information of small molecules can reflect relative position of atoms more directly, which affects molecular properties. In this work, we present a new deep learning model called Drug3D-DTI for drug-target interaction prediction. Drug3D-DTI takes advantage of molecular spatial information, i.e., atom proximity in three-dimensional (3D) structures. We comprehensively evaluated the performance of Drug3D-DTI on two datasets with two tasks of regression and classification. In particular, we compared Drug3D-DTI with several existing methods including the two cutting-edge methods for compound-protein interaction prediction. From the experimental results, Drug3D-DTI clearly outperformed other methods under all settings. Further, this performance improvement was validated by ablation experiments and a case study. The implementation of Drug3D-DTI is available at (https://***/zhiruiliao/Drug3D-DTI). © 2021 IEEE.

关键词： Molecules