检索结果-内蒙古大学图书馆

Prior Visual Relationship Reasoning For Visual Question Answering

学校读者我要写书评

暂无评论

Prior Visual Relationship Reasoning For Visual Question Answ...

IEEE International Conference on Image Processing

作者： Zhuoqian Yang Zengchang Qin Jing Yu Tao Wan Robotics Institute Carnegie Mellon University Pittsburgh PA USA Intelligent Computing and Machine Learning Lab School of ASEE Beihang University China Institute of Information Engineering CAS China School of Biological Science and Medical Engineering Beihang University Beijing China

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

Visual Question Answering (VQA) is a representative task of cross-modal reasoning where an image and a free-form question in natural language are presented and the correct answer needs to be determined using both visual and textual information. One of the key issues of VQA is to reason with semantic clues in the visual content under the guidance of the question. In this paper, we propose Scene Graph Convolutional Network (SceneGCN) to jointly reason the object properties and their semantic relations for the correct answer. The visual relationship is projected into a deep learned semantic space constrained by visual context and language priors. Based on comprehensive experiments on two challenging datasets: GQA and VQA 2.0, we demonstrate the effectiveness and interpretability of the new model.

关键词： Visualization Semantics Convolution Cognition Knowledge discovery Benchmark testing Measurement

Double variance reduction: a smoothing trick for composite optimization problems without first-order gradient 24

学校读者我要写书评

暂无评论

Double variance reduction: a smoothing trick for composite o...

Proceedings of the 41st International Conference on machine learning

作者： Hao Di Haishan Ye Yueling Zhang Xiangyu Chang Guang Dai Ivor W. Tsang Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China and SGIT AI Lab State Grid Corporation of China International Business School Beijing Foreign Studies University Beijing China Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China CFAR and IHPC Agency for Science Technology and Research (A*STAR) Singapore and College of Computing and Data Science NTU Singapore

Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods. However, in composite optimization problems, ZO methods encounter an additional variance called the coordinate-wise variance, which stems from the random gradient estimation. To reduce this variance, prior works require estimating all partial derivatives, essentially approximating FO information. This approach demands O(d) function evaluations (d is the dimension size), which incurs substantial computational costs and is prohibitive in high-dimensional scenarios. This paper proposes the Zeroth-order Proximal Double Variance Reduction (ZPDVR) method, which utilizes the averaging trick to reduce both sampling and coordinate-wise variances. Compared to prior methods, ZPDVR relies solely on random gradient estimates, calls the stochastic zeroth-order oracle (SZO) in expectation O(1) times per iteration, and achieves the optimal O(d(n+κ) log(1/ε)) SZO query complexity in the strongly convex and smooth setting, where κ represents the condition number and ε is the desired accuracy. Empirical results validate ZPDVR's linear convergence and demonstrate its superior performance over other related methods.

关键词：

A novel texture image segmentation model based on multi-scale structure

学校读者我要写书评

暂无评论

A novel texture image segmentation model based on multi-scal...

International Conference on Multisensor Fusion and Integration for intelligent Systems (MFI)

作者： Hai Min Xiao-Feng Wang De-Shuang Huang Department of Automation University of Science and Technology of China Hefei Anhui China Intelligent Computing Lab Chinese Academy of Sciences Department of Computer Science and Technology Hefei University Hefei Anhui China Machine Learning and Systems Biology Laboratory Tongji University Shanghai China

ISBN: (纸本)9781479967339

Using neighborhood information from different scales in an effective way for object segmentation, however, remains a difficult problem. In this paper, we propose a novel method which incorporates the multi-scale structure into intensity information. The multi-scale structure is proposed as structure information to describe the texture feature of image. We select eight points as the sample components of each layer and further solve the maximum variance between eight components and center pixel. In addition, the multi-scale structure can be suitably used to extract the texture information of image. Then, by combining texture information with intensity information, we use level set method to obtain the segmentation results. Experiments using synthetic and real natural scene images demonstrate the superior performance of the proposed method.

关键词： Image segmentation Level set Feature extraction Gabor filters Tensile stress Visualization Image color analysis

DAM: Deliberation, Abandon and Memory Networks for Generating Detailed and Non-repetitive Responses in Visual Dialogue

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jiang, Xiaoze Yu, Jing Sun, Yajing Qin, Zengchang Zhu, Zihao Hu, Yue Wu, Qi Institute of Information Engineering Chinese Academy of Sciences Beijing China Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China AI Research Codemao Inc University of Adelaide Australia

Visual Dialogue task requires an agent to be engaged in a conversation with human about an image. The ability of generating detailed and non-repetitive responses is crucial for the agent to achieve human-like conversation. In this paper, we propose a novel generative decoding architecture to generate high-quality responses, which moves away from decoding the whole encoded semantics towards the design that advocates both transparency and flexibility. In this architecture, word generation is decomposed into a series of attention-based information selection steps, performed by the novel recurrent Deliberation, Abandon and Memory (DAM) module. Each DAM module performs an adaptive combination of the response-level semantics captured from the encoder and the word-level semantics specifically selected for generating each word. Therefore, the responses contain more detailed and non-repetitive descriptions while maintaining the semantic accuracy. Furthermore, DAM is flexible to cooperate with existing visual dialogue encoders and adaptive to the encoder structures by constraining the information selection mode in DAM. We apply DAM to three typical encoders and verify the performance on the VisDial v1.0 dataset. Experimental results show that the proposed models achieve new state-of-the-art performance with high-quality responses. The code is available at https://***/JXZe/DAM. Copyright © 2020, The Authors. All rights reserved.

关键词： Signal encoding

Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Di, Hao Ye, Haishan Zhang, Yueling Chang, Xiangyu Dai, Guang Tsang, Ivor W. Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China China International Business School Beijing Foreign Studies University Beijing China Singapore College of Computing and Data Science NTU Singapore

Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods. However, in composite optimization problems, ZO methods encounter an additional variance called the coordinate-wise variance, which stems from the random gradient estimation. To reduce this variance, prior works require estimating all partial derivatives, essentially approximating FO information. This approach demands O(d) function evaluations (d is the dimension size), which incurs substantial computational costs and is prohibitive in high-dimensional scenarios. This paper proposes the Zeroth-order Proximal Double Variance Reduction (ZPDVR) method, which utilizes the averaging trick to reduce both sampling and coordinate-wise variances. Compared to prior methods, ZPDVR relies solely on random gradient estimates, calls the stochastic zeroth-order oracle (SZO) in expectation O(1) times per iteration, and achieves the optimal O(d(n+κ) log( 1∈ )) SZO query complexity in the strongly convex and smooth setting, where κ represents the condition number and ∈ is the desired accuracy. Empirical results validate ZPDVR's linear convergence and demonstrate its superior performance over other related methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Iterative methods

Can Gaussian sketching converge faster on a preconditioned landscape? 24

学校读者我要写书评

暂无评论

Can Gaussian sketching converge faster on a preconditioned l...

Proceedings of the 41st International Conference on machine learning

作者： Yilong Wang Haishan Ye Guang Dai Ivor W. Tsang Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China and SGIT AI Lab State Grid Corporation of China SGIT AI Lab State Grid Corporation of China CFAR and IHPC Agency for Science Technology and Research (A*STAR) Singapore and College of Computing and Data Science NTU Singapore

This paper focuses on the large-scale optimization which is very popular in the big data era. The gradient sketching is an important technique in the large-scale optimization. Specifically, the random coordinate descent algorithm is a kind of gradient sketching method with the random sampling matrix as the sketching matrix. In this paper, we propose a novel gradient sketching called GSGD (Gaussian Sketched Gradient Descent). Compared with the classical gradient sketching methods such as the random coordinate descent and SEGA (Hanzely et al., 2018), our GSGD does not require the importance sampling but can achieve a fast convergence rate matching the ones of these methods with importance sampling. Furthermore, if the objective function has a non-smooth regularization term, our GSGD can also exploit the implicit structure information of the regularization term to achieve a fast convergence rate. Finally, our experimental results substantiate the effectiveness and efficiency of our algorithm.

关键词：

Emotion classification with data augmentation using generative adversarial networks

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhu, Xinyue Liu, Yifan Qin, Zengchang Li, Jiahong School of Electronic Engineering Bejing University of Posts and Telecommunications Beijing100876 China Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing100191 China Beijing San Kuai Yun Technology Co. Ltd. Hengdian Building No.4 Wangjing East RD Chaoyang District Beijing China

It is a difficult task to classify images with multiple class labels using only a small number of labeled examples, especially when the label (class) distribution is imbalanced. Emotion classification is such an example of imbalanced label distribution, because some classes of emotions like disgusted are relatively rare comparing to other labels like happy or sad. In this paper, we propose a data augmentation method using generative adversarial networks (GAN). It can complement and complete the data manifold and find better margins between neighboring classes. Specifically, we design a framework using a CNN model as the classifier and a cycle-consistent adversarial networks (CycleGAN) as the generator. In order to avoid gradient vanishing problem, we employ the least-squared loss as adversarial loss. We also propose several evaluation methods on three benchmark datasets to validate GAN's performance. Empirical results show that we can obtain 5%∼10% increase in the classification accuracy after employing the GAN-based data augmentation techniques. Copyright © 2017, The Authors. All rights reserved.

关键词： Generative adversarial networks

Tackling Instance-Dependent label Noise via a Universal Probabilistic Model

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Qizhou Han, Bo Liu, Tongliang Niu, Gang Yang, Jian Gong, Chen Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of MoE School of Computer Science and Engineering Nanjing University of Science and Technology China Department of Computer Science Hong Kong Baptist University Hong Kong Trustworthy Machine Learning Lab School of Computer Science Faculty of Engineering The University of Sydney Australia Japan Department of Computing Hong Kong Polytechnic University Hong Kong

The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learning methods with label noise either employ ad-hoc heuristics or restrict to specific noise assumptions. However, more general situations, such as instance-dependent label noise, have not been fully explored, as scarce studies focus on their label corruption process. By categorizing instances into confusing and unconfusing instances, this paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. The resultant model can be realized by DNNs, where the training procedure is accomplished by employing an alternating optimization algorithm. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness over state-of-the-art counterparts. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

Advanced Topics in Science and Technology in China

学校读者我要写书评

暂无评论

Preface

Advanced Topics in Science and Technology in China 2014年 vii页

作者： Qin, Zengchang Tang, Yongchuan Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China College of Computer Science Zhejiang University HangzhouZhejiang China