检索结果-内蒙古大学图书馆

Saliency Detection via Absorbing Markov Chain With Learnt Transition Probability

IEEE TRANSACTIONS ON IMAGE PROCESSING 2018年第2期27卷 987-998页

作者： Zhang, Lihe Ai, Jianwu Jiang, Bowen Lu, Huchuan Li, Xiukui Dalian Univ Technol Sch Informat & Commun Engn Dalian 116024 Peoples R China AutoNavi Software Co Ltd Beijing 100102 Peoples R China

In this paper, we propose a bottom-up saliency model based on absorbing Markov chain (AMC). First, a sparsely connected graph is constructed to capture the local context information of each node. All image boundary nodes and other nodes are, respectively, treated as the absorbing nodes and transient nodes in the absorbing Markov chain. Then, the expected number of times from each transient node to all other transient nodes can be used to represent the saliency value of this node. The absorbed time depends on the weights on the path and their spatial coordinates, which are completely encoded in the transition probability matrix. Considering the importance of this matrix, we adopt different hierarchies of deep features extracted from fully convolutional networks and learn a transition probability matrix, which is called learnt transition probability matrix. Although the performance is significantly promoted, salient objects are not uniformly highlighted very well. To solve this problem, an angular embedding technique is investigated to refine the saliency results. Based on pairwise local orderings, which are produced by the saliency maps of AMC and boundary maps, we rearrange the global orderings (saliency value) of all nodes. Extensive experiments demonstrate that the proposed algorithm outperforms the state-of-the-art methods on six publicly available benchmark data sets.

关键词： Salient object detection absorbing Markov chain transition probability matrix angular embedding

来源：评论

学校读者我要写书评

暂无评论

Provably robust estimation of modulo 1 samples of a smooth function with applications to phase unwrapping

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2020年第1期21卷 1-77页

作者： Cucuringu, Mihai Tyagi, Hemant Alan Turing Inst London England Univ Oxford Dept Stat & Math Inst Oxford England INRIA Lille Nord Europe Lille France

Consider an unknown smooth function f : [0, 1](d) -> R, and assume we are given n noisy mod 1 samples of f, i.e., y(i) = (f (x(i))+eta(i)) mod 1, for x(i) is an element of [0, 1] (d), where eta(i) denotes the noise. Given the samples (x(i), y(i))(i=)(n)(1) , our goal is to recover smooth, robust estimates of the clean samples f (x(i)) mod 1. We formulate a natural approach for solving this problem, which works with angular embeddings of the noisy mod 1 samples over the unit circle, inspired by the angular synchronization framework. This amounts to solving a smoothness regularized least-squares problem - a quadratically constrained quadratic program (QCQP) - where the variables are constrained to lie on the unit circle. Our proposed approach is based on solving its relaxation, which is a trust-region sub-problem and hence solvable efficiently. We provide theoretical guarantees demonstrating its robustness to noise for adversarial, as well as random Gaussian and Bernoulli noise models. To the best of our knowledge, these are the first such theoretical results for this problem. We demonstrate the robustness and efficiency of our proposed approach via extensive numerical simulations on synthetic data, along with a simple least-squares based solution for the unwrapping stage, that recovers the original samples of f (up to a global shift). It is shown to perform well at high levels of noise, when taking as input the denoised modulo 1 samples. Finally, we also consider two other approaches for denoising the modulo 1 samples that leverage tools from Riemannian optimization on manifolds, including a Burer-Monteiro approach for a semi-definite programming relaxation of our formulation. For the two-dimensional version of the problem, which has applications in synthetic aperture radar interferometry (InSAR), we are able to solve instances of real-world data with a million sample points in under 10 seconds, on a personal laptop.

关键词： quadratically constrained quadratic programming (QCQP) trust-region subproblem angular embedding phase unwrapping semidefinite programming angular synchronization

来源：评论

学校读者我要写书评

暂无评论

The identity-level angular triplet loss for cross-age face recognition

引用

APPLIED INTELLIGENCE 2022年第6期52卷 6330-6339页

作者： Chen, Xiaoyu Lau, Henry Y. K. Univ Hong Kong Dept Ind & Mfg Syst Engn Hong Kong Peoples R China

Despite promising progress has been achieved on face recognition problems, cross-age face recognition remains a challenging task due to its age variations. Human appearances change along with the age growing process, which increases the difficulty of recognition tasks. Existing methods mainly focus on synthesizing new facial images according to different age levels or isolating age-related features and identity related features. In this paper, we propose an identity-level angular triplet loss for cross-age face recognition. The facial images are projected to an embedding space where the angle between feature embeddings can represent similarities of images. Different from Euclidean distance metric, the angular metric used in our method guides the model to learn discriminative features under large intra-class discrepancy. Angles between intra-class embeddings are reduced while that between inter-class are enlarged. The selection of good triplets is conducted on an identity-level rather than instance-level with a moderate positive mining strategy. Experiments are conducted on cross-age databases and results prove the effectiveness of our method.

关键词： Cross-age face recognition angular embedding Triplet loss Metric learning

来源：评论

学校读者我要写书评

暂无评论

A salient object detection framework using linear quadratic regulator controller*

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2021年 79卷 103259-103259页

作者： Moradi, Morteza Bayat, Farhad Charmi, Mostafa Univ Zanjan Dept Elect Engn Zanjan Iran

In this paper, a novel salient object detection framework based on Linear Quadratic Regulator (LQR) controller is proposed. The major goal of this research is to take advantage of optimal control theory for improving the performance of detecting salient objects in images. In this regard, for the sake of detection of salient and non salient regions, two LQR-based control systems are employed. In the proposed framework, for the initialization of the control systems, background and foreground estimations have been done with two different strategies. Doing so, we would ultimately have more effective distinction between those regions. After the initialization step, the control systems refine both estimations in parallel until reaching a steady state for each of them. Within the mentioned process, by using optimal control concept, specifically LQR controller (for the first time in the field), control signals which are in charge of determining saliency values, would be constantly optimized. At the end, the raw saliency map will be generated by combination of background and foreground optimized initial maps. Finally, the integrated saliency map will be refined by using angular embedding method. The experimental evaluations on three benchmark datasets shows that the proposed framework performs well and introduces comparable results with some deep learning based methods.

关键词： Salient object detection Control system Linear quadratic regulator Optimal control angular embedding

来源：评论

学校读者我要写书评

暂无评论

Csf: global-local shading orders for intrinsic image decomposition

引用

MACHINE VISION AND APPLICATIONS 2024年第1期35卷 4-4页

作者： Zhang, Handan Liu, Tie Liu, Yuanliu Yuan, Zejian Capital Normal Univ Coll Informat Engn Beijing 10048 Peoples R China Xi An Jiao Tong Univ Coll Artificial Intelligence Xian 710049 Shaanxi Peoples R China

Intrinsic image decomposition faces the long-standing challenge from the coupling of the components of the image-the surface albedo, direct illumination, and ambient illumination in the observed image. Without knowing the absolute values of the image components, we propose inferring shading by ordering pixels by relative brightness. The pairwise shading orders are estimated in two ways: brightness order and low-order fittings of the local shading field. The brightness order is a nonlocal metric that can be used to compare any two pixels, including those with different reflectances and shadings. Low-order fittings are used for pixel pairs within local regions of smooth shading. They can capture the global order structure and local variations in the shading when used together. To integrate the pairwise orders into a globally consistent order, we propose a Consistency-aware Selective Fusion method. The iterative selection process solves the inconsistencies between pairwise orders obtained using different estimation methods. To avoid polluting the global order, inconsistent or unreliable pairwise orders will be automatically excluded from the fusion. Experimental results show that the proposed model effectively recovers the shading, including deep shadows, on the MIT Intrinsic Image dataset. Moreover, our model works well on natural images from the IIW, UIUC Shadow, and NYU-depth datasets, where the colors of direct lights and ambient lights are quite different.

关键词： Intrinsic image decomposition Shading order Consistency-aware selective fusion angular embedding

来源：评论

学校读者我要写书评

暂无评论

Provably robust estimation of modulo 1 samples of a smooth function with applications to phase unwrapping

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2020年第1期21卷 1148-1224页

作者： Mihai Cucuringu Hemant Tyagi The Alan Turing Institute London UK and Department of Statistics and Mathematical Institute University of Oxford Oxford UK INRIA Lille - Nord Europe Lille France

Consider an unknown smooth function f : [0, 1]d → R, and assume we are given n noisy mod 1 samples of f, i.e., yi = (f(xi)+ηi) mod 1, for xi ∈ [0, 1]d, where ηi denotes the noise. Given the samples (xi, yi)ni=1, our goal is to recover smooth, robust estimates of the clean samples f(xi) mod 1. We formulate a natural approach for solving this problem, which works with angular embeddings of the noisy mod 1 samples over the unit circle, inspired by the angular synchronization framework. This amounts to solving a smoothness regularized least-squares problem - a quadratically constrained quadratic program (QCQP) - where the variables are constrained to lie on the unit circle. Our proposed approach is based on solving its relaxation, which is a trust-region sub-problem and hence solvable efficiently. We provide theoretical guarantees demonstrating its robustness to noise for adversarial, as well as random Gaussian and Bernoulli noise models. To the best of our knowledge, these are the first such theoretical results for this problem. We demonstrate the robustness and efficiency of our proposed approach via extensive numerical simulations on synthetic data, along with a simple least-squares based solution for the unwrapping stage, that recovers the original samples of f (up to a global shift). It is shown to perform well at high levels of noise, when taking as input the denoised modulo 1 ***, we also consider two other approaches for denoising the modulo 1 samples that leverage tools from Riemannian optimization on manifolds, including a Burer-Monteiro approach for a semidefinite programming relaxation of our formulation. For the two-dimensional version of the problem, which has applications in synthetic aperture radar interferometry (InSAR), we are able to solve instances of real-world data with a million sample points in under 10 seconds, on a personal laptop.

关键词： quadratically constrained quadratic programming (QCQP) trust-region subproblem angular embedding phase unwrapping semidefinite programming angular synchronization

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：