检索结果-内蒙古大学图书馆

RGBT Tracking via Progressive Fusion Transformer with Dynamically Guided Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhu, Yabin Li, Chenglong Wang, Xiao Tang, Jin Huang, Zhixiang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes School of Electronic and Information Engineering Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

Existing Transformer-based RGBT tracking methods either use cross-attention to fuse the two modalities, or use self-attention and cross-attention to model both modality-specific and modality-sharing information. However, the significant appearance gap between modalities limits the feature representation ability of certain modalities during the fusion process. To address this problem, we propose a novel Progressive Fusion Transformer called ProFormer, which progressively integrates single-modality information into the multimodal representation for robust RGBT tracking. In particular, ProFormer first uses a self-attention module to collaboratively extract the multimodal representation, and then uses two cross-attention modules to interact it with the features of the dual modalities respectively. In this way, the modality-specific information can well be activated in the multimodal representation. Finally, a feed-forward network is used to fuse two interacted multimodal representations for the further enhancement of the final multimodal representation. In addition, existing learning methods of RGBT trackers either fuse multimodal features into one for final classification, or exploit the relationship between unimodal branches and fused branch through a competitive learning strategy. However, they either ignore the learning of single-modality branches or result in one branch failing to be well optimized. To solve these problems, we propose a dynamically guided learning algorithm that adaptively uses well-performing branches to guide the learning of other branches, for enhancing the representation ability of each branch. Extensive experiments demonstrate that our proposed ProFormer sets a new state-of-the-art performance on RGBT210, RGBT234, LasHeR, and VTUAV datasets. In particular, the improvements of ProFormer on the LasHeR dataset are up to +6.2%/+ 4.1% in PR/SR compared with existing best RGBT tracker. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning 24

学校读者我要写书评

暂无评论

Towards High-resolution 3D Anomaly Detection via Group-Level...

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9798400706868

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3D-AD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. © 2024 ACM.

关键词： Contrastive Learning

Molecule optimization via multi-objective evolutionary in implicit chemical space

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xia, Xin Su, Yansen Zheng, Chunhou Zeng, Xiangxiang The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Anhui University Hefei230601 China College of Computer Science and Electronic Engineering Hunan University China

Machine learning methods have been used to accelerate the molecule optimization process. However, efficient search for optimized molecules satisfying several properties with scarce labeled data remains a challenge for machine learning molecule optimization. In this study, we propose MOMO, a multi-objective molecule optimization framework to address the challenge by combining learning of chemical knowledge with Pareto-based multi-objective evolutionary search. To learn chemistry, it employs a self-supervised codec to construct an implicit chemical space and acquire the continues representation of molecules. To explore the established chemical space, MOMO uses multiobjective evolution to comprehensively and efficiently search for similar molecules with multiple desirable properties. We demonstrate the high performance of MOMO on four multi-objective property and similarity optimization tasks, and illustrate the search capability of MOMO through case studies. Remarkably, our approach significantly outperforms previous approaches in optimizing three objectives simultaneously. The results show the optimization capability of MOMO, suggesting to improve the success rate of lead molecule optimization. Copyright © 2022, The Authors. All rights reserved.

关键词： Molecules

Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Jilan Hou, Junlin Zhang, Yuejie Feng, Rui Wang, Yi Qiao, Yu Xie, Weidi School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Shanghai AI Laboratory China Shanghai Jiaotong University China

In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. The main contributions are as follows: First, we propose a transformer-based model for OVS, termed as OVSegmentor, which only exploits web-crawled image-text pairs for pre-training without using any mask annotations. OVSegmentor assembles the image pixels into a set of learnable group tokens via a slot-attention based binding module, and aligns the group tokens to the corresponding caption embedding. Second, we propose two proxy tasks for training, namely masked entity completion and cross-image mask consistency. The former aims to infer all masked entities in the caption given the group tokens, that enables the model to learn fine-grained alignment between visual groups and text entities. The latter enforces consistent mask predictions between images that contain shared entities, which encourages the model to learn visual invariance. Third, we construct CC4M dataset for pre-training by filtering CC12M with frequently appeared entities, which significantly improves training efficiency. Fourth, we perform zero-shot transfer on three benchmark datasets, PASCAL VOC 2012, PASCAL Context, and COCO Object. Our model achieves superior segmentation results over the state-of-the-art method by using only 3% data (4M vs 134M) for pre-training. Code and pre-trained models will be released for future research. © 2023, CC BY.

关键词： Semantics

High-Accurate and Eﬀicient Numerical Algorithms for the Self-Consistent Field Theory of Liquid-Crystalline Polymers

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Tan, Liwei He, Zhijuan Wang, Xin Jiang, Kai Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China School of Mathematical Sciences Shanghai Jiao Tong University Shanghai200240 China

In this paper, we develop and investigate numerical methods for the self-consistent field theory (SCFT) of liquid crystalline polymers. Both the Flory-Huggins interaction potential and the Maier-Saupe orientational interaction are considered, enabling simultaneous exploration of microphase separation and liquid crystalline order in these systems. The main challenge in numerically solving this complex system lies in solving 6-dimensional (3D spatial + 2D orientation + 1D time) partial differential equations and performing nonlinear iterations to optimize the fields. We present ten numerical algorithms for solving high-dimensional PDEs and give an evaluation criterion of choosing the most appropriate PDE solver both from theoretical and numerical performance. Results demonstrate that coupling the fourth-order Runge-Kutta scheme with Fourier pseudo-spectral methods and spherical harmonic transformations is superior compared to other algorithms. We develop two nonlinear iteration schemes, alternating direction iteration method and Anderson mixing method, and design an adaptive technique to enhance the stability of the Anderson mixing method. Moreover, the cascadic multi-level (CML) technique further accelerates the SCFT computation when applied to these iteration methods. Meanwhile, an approach to optimize the computational domain is developed. To demonstrate the power of our approaches, we investigate the self-assembled behaviors of flexible-semiflexible diblock copolymers in 4, 5, 6-dimensional simulations. Numerical results illustrate the eﬀiciency of our proposed method. © 2024, The Authors. All rights reserved.

关键词： Mixing

Quasiperiodic Symmetric Tilt FCC Grain Boundaries

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zou, Wenwen Zhang, Juan Xu, Jie Jiang, Kai Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China LSEC NCMIS Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

In this work, we investigate [110] symmetric tilt FCC grain boundaries (GBs) by a recently developed approach for quasiperiodic interfaces using the Landau-Brazovskii model. On special tilt angles associated with quadratic algebraic numbers, quasiperiodic GBs exhibit generalized Fibonacci substitution rules. The transition mechanism from quasiperiodic GBs to periodic GBs is explored through sphere offsets and spectral coalescence. We also propose an accurate method to calculate the GB energy for arbitrary tilt angle and analyze the factors affecting the GB energy. The revealing GB energy change is continue along with tilt angle except periodic GBs. © 2024, CC BY-NC-SA.

关键词： Grain boundaries

AGMR-Net: Attention Guided Multiscale Recovery framework for stroke segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Du, Xiuquan Ma, Kunpeng Song, Yuhui Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Anhui Hefei230601 China School of Computer Science and Technology Anhui University Anhui Hefei230601 China

Automatic and accurate lesion segmentation is critical for clinically estimating the lesion statuses of stroke diseases and developing appropriate diagnostic systems. Although existing methods have achieved remarkable results, further adoption of the models is hindered by: (1) inter-class indistinction, the normal brain tissue resembles the lesion in appearance. (2) intra-class inconsistency, large variability exists between different areas of the lesion. To solve these challenges in stroke segmentation, we propose a novel method, namely Attention Guided Multiscale Recovery framework (AGMR-Net) in this paper. Firstly, a coarse-grained patch attention module in the encoding is adopted to get a patch-based coarse-grained attention map in a multi-stage explicitly supervised way, enabling target spatial context saliency representation with a patch-based weighting technique that eliminates the effect of intra-class inconsistency. Secondly, to obtain a more detailed boundary partitioning to solve the challenge of the inter-class indistinction, a newly designed cross-dimensional feature fusion module is used to capture global contextual information to further guide the selective aggregation of 2D and 3D features, which can compensate for the lack of boundary learning capability of 2D convolution. Lastly, in the decoding stage, an innovative designed multi-scale deconvolution upsampling instead of linear interpolation enhances the recovery of target space and boundary information. The AGMR-Net is evaluated on the open dataset Anatomical Tracings of Lesions-After-Stroke (ATLAS), achieving the highest dice similarity coefficient (DSC) score of 0.594, Hausdorff distance of 27.005 mm, and average symmetry surface distance of 7.137 mm, which demonstrate that our proposed method outperforms other state-of-the-art methods and has great potential in the diagnosis of stroke. Copyright © 2022, The Authors. All rights reserved.

关键词： Recovery

Learning Common and Label-Specific Features for Label Distribution Learning with Correlation Information

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wu, Yilin Lin, Yaojin Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Key Laboratory of Data Science and Intelligence Application Minnan Normal University Zhangzhou363000 China

Label distribution learning quantifies the label space for each instance and has wide applicability in different fields. However, most existing work primarily focuses on common features, ignores the significance of label-specific features. Meanwhile, label correlation is well used in these work, but they still have limitations in capturing instance correlation. Therefore, in this paper, we propose a novel approach for label distribution learning to learn common and label-specific features with correlation information i.e. instance correlation and label correlation. First, we conduct $\ell_{2,1}-$norm regularization to select common and label-specific features, simultaneously. Then, we implement an optimization function to identify instance correlation in feature space. In addition, label correlation is collected with Pearson correlation coefficient. Finally, we design an objective function that enables the joint learning of common and label-specific features while leveraging correlation information. Comprehensive experiments manifest the superiority of our proposed approach against other well-established label distribution learning algorithms. © 2024, The Authors. All rights reserved.

关键词： Learning algorithms