检索结果-内蒙古大学图书馆

Triplet Decoupling Network for Masked Face Verification

学校读者我要写书评

暂无评论

Triplet Decoupling Network for Masked Face Verification

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Yuechao Guo Jie Wen Jingyong Su Yong Xu Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Shenzhen Shenzhen China Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen & Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9781665426312

Face verification has been widely applied to identity authentication in many areas. However, due to the mask information embedded into the facial feature representation, existing face verification systems generally fail to identify the faces covered by masks during the COVID-19 coronavirus epidemic period. To address this issue, we propose a new triplet decoupling network (TDN) for the challenging masked face verification. Different from existing works, our proposed TDN seeks to remove the mask information included in extracted facial features by feature decoupling, such that more discriminative facial feature representations can be obtained for masked face verification. In addition, a new triplet similarity margin loss (TSM) is designed to enlarge the margin between the intra-class similarity and the inter-class similarity of faces. Experimental results show that the proposed method significantly outperforms the other state-of-the-art methods on masked face datasets, which demonstrates the effectiveness of our proposed method.

关键词： COVID-19 Epidemics Authentication Feature extraction Data mining Artificial intelligence Faces

Multi-contrast MRI super-resolution via a multi-stage integration network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Feng, Chun-Mei Fu, Huazhu Yuan, Shuhao Xu, Yong Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen China Inception Institute of Artificial Intelligence

Super-resolution (SR) plays a crucial role in improving the image quality of magnetic resonance imaging (MRI). MRI produces multi- contrast images and can provide a clear display of soft tissues. However, current super-resolution methods only employ a single contrast, or use a simple multi-contrast fusion mechanism, ignoring the rich relations among different contrasts, which are valuable for improving SR. In this work, we propose a multi-stage integration network (i.e., MINet) for multi-contrast MRI SR, which explicitly models the dependencies be- tween multi-contrast images at different stages to guide image SR. In particular, our MINet first learns a hierarchical feature representation from multiple convolutional stages for each of different-contrast image. Subsequently, we introduce a multi-stage integration module to mine the comprehensive relations between the representations of the multi- contrast images. Specifically, the module matches each representation with all other features, which are integrated in terms of their similarities to obtain an enriched representation. Extensive experiments on fastMRI and real-world clinical datasets demonstrate that 1) our MINet outper- forms state-of-the-art multi-contrast SR methods in terms of various metrics and 2) our multi-stage integration module is able to excavate complex interactions among multi-contrast features at different stages, leading to improved target-image quality. © 2021, CC BY.

关键词： Optical resolving power

Cross-view Graph Contrastive Representation Learning on Partially Aligned Multi-view Data

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Yiming Chang, Dongxia Fu, Zhiqiang Wen, Jie Zhao, Yao Institute of Information Science Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen Shenzhen China

Multi-view representation learning has developed rapidly over the past decades and has been applied in many fields. However, most previous works assumed that each view is complete and aligned. This leads to an inevitable deterioration in their performance when encountering practical problems such as missing or unaligned views. To address the challenge of representation learning on partially aligned multi-view data, we propose a new cross-view graph contrastive learning framework, which integrates multi-view information to align data and learn latent representations. Compared with current approaches, the proposed method has the following merits: (1) our model is an end-to-end framework that simultaneously performs view-specific representation learning via view-specific autoencoders and cluster-level data aligning by combining multi-view information with the cross-view graph contrastive learning;(2) it is easy to apply our model to explore information from three or more modalities/sources as the cross-view graph contrastive learning is devised. Extensive experiments conducted on several real datasets demonstrate the effectiveness of the proposed method on the clustering and classification tasks. © 2022, CC BY.

关键词： Deterioration

Learned descriptor using dynamical exponential algorithm 2

学校读者我要写书评

暂无评论

Learned descriptor using dynamical exponential algorithm

2nd International Conference on Artificial Intelligence, Information Processing and Cloud Computing, AIIPCC 2021

作者： Yin, Jianhua Liu, Cong Wen, Jie Chen, Junhong Jiang, Jun Liu, Hui Zhu, Longzhen School of Computer Science and Technology Harbin Institute of Technology Shenzhen Shenzhen518055 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen Shenzhen518055 China Peng Cheng Laboratory Shenzhen518055 China Hengfeng Bank Co. Ltd. Shanghai200000 China

ISBN: (纸本)9783800756162

Recent works improve the performance of learned descriptors by the triplet loss function and make some effort in finding the hard negative samples. However, these methods pay less attention to the weight parameter of the loss function to improve the stability of learned descriptors. Unstable descriptors can cause mismatching. To solve the problem, we design a dynamical exponential algorithm (DEA) and introduce the algorithm into the triplet loss function. This algorithm can make that the distance between nonmatching descriptors is exceeded to the distance between matching descriptors. It can improve the stability of the learned descriptor by increasing the difference between two distances. We demonstrate that the performance of the consistent descriptors reached state-of-the-art on various datasets. © 2021 AIIPCC 2021 - 2nd International Conference on Artificial Intelligence, Information Processing and Cloud Computing. All rights reserved.

关键词： Artificial intelligence

Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Lintai Zhang, Qijian Hou, Junhui Xu, Yong The Department of Computer Science City University of Hong Kong Hong Kong The Bio-Computing Research Center Harbin Institute of Technology Shenzhen Guangdong Shenzhen518055 China The Shenzhen Key Laboratory of Visual Object Detection and Recognition Guangdong Shenzhen518055 China

Point clouds captured by scanning devices are often incomplete due to occlusion. To overcome this limitation, point cloud completion methods have been developed to predict the complete shape of an object based on its partial input. These methods can be broadly classified as supervised or unsupervised. However, both categories require a large number of 3D complete point clouds, which may be difficult to capture. In this paper, we propose Cross-PCC, an unsupervised point cloud completion method without requiring any 3D complete point clouds. We only utilize 2D images of the complete objects, which are easier to capture than 3D complete and clean point clouds. Specifically, to take advantage of the complementary information from 2D images, we use a single-view RGB image to extract 2D features and design a fusion module to fuse the 2D and 3D features extracted from the partial point cloud. To guide the shape of predicted point clouds, we project the predicted points of the object to the 2D plane and use the foreground pixels of its silhouette maps to constrain the position of the projected points. To reduce the outliers of the predicted point clouds, we propose a view calibrator to move the points projected to the background into the foreground by the single-view silhouette image. To the best of our knowledge, our approach is the first point cloud completion method that does not require any 3D supervision. The experimental results of our method are superior to those of the state-of-the-art unsupervised methods by a large margin. Moreover, our method even achieves comparable performance to some supervised methods. We will make the source code publicly available at https://***/ltwu6/cross-pcc. Copyright © 2022, The Authors. All rights reserved.

关键词： Unsupervised learning

Diffusion-based missing-view generation with the application on incomplete multi-view clustering 24

学校读者我要写书评

暂无评论

Diffusion-based missing-view generation with the application...

Proceedings of the 41st International Conference on Machine Learning

作者： Jie Wen Shijie Deng Waikeung Wong Guoqing Chao Chao Huang Lunke Fei Yong Xu Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen China School of Fashion and Textiles The Hong Kong Polytechnic University Hong Kong and Laboratory for Artificial Intelligence in Design Hong Kong School of Computer Science and Technology Harbin Institute of Technology Weihai China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen China School of Computer Science and Technology Guangdong University of Technology Guangzhou China

As a branch of clustering, multi-view clustering has received much attention in recent years. In practical applications, a common phenomenon is that partial views of some samples may be missing in the collected multi-view data, which poses a severe challenge to design the multi-view learning model and explore complementary and consistent information. Currently, most of the incomplete multi-view clustering methods only focus on exploring the information of available views while few works study the missing view recovery for incomplete multi-view learning. To this end, we propose an innovative diffusion-based missing view generation (DMVG) network. Moreover, for the scenarios with high missing rates, we further propose an incomplete multi-view data augmentation strategy to enhance the recovery quality for the missing views. Extensive experimental results show that the proposed DMVG can not only accurately predict missing views, but also further enhance the subsequent clustering performance in comparison with several state-of-the-art incomplete multi-view clustering methods.

关键词：

Normal Distribution Function on Descriptor Extraction 11th

学校读者我要写书评

暂无评论

Normal Distribution Function on Descriptor Extraction

11th International Conference on Image and Graphics, ICIG 2021

作者： Yin, Jianhua Liu, Cong Jiang, Jun Wen, Jie Yang, Lihang Zhu, Shilong School of Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China Peng Cheng Laboratory Shenzhen518055 China Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen518055 China College of Big Data and Information Engineering Guizhou University Guizhou Guiyang550025 China

ISBN: (纸本)9783030873578

The triplet-loss function is widely used in fields of descriptor extraction in recent years and owing to its good performance in various databases. However, some recent works make less effort on the relationship of adjacent descriptors from the same sample, which leads to the instability of descriptors and results in the mismatching problem in practical applications. To solve this problem, we introduce the topological relationship with the Normal Distribution Function (NDF) into the triplet loss function. The loss function establishes the relationship of descriptors from the same sample and considers the interrelation of descriptors from different types of samples. Furthermore, to increase the calculation speed, we normalize the algorithm NDF. Finally, we propose the triplet-loss function on three databases. These results demonstrate that our algorithm obtains better performance than state-of-the-art methods. © 2021, Springer Nature Switzerland AG.

关键词： Distribution functions

Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Suyi Jiang, Chenyi Wang, Shidong Long, Yang Zhang, Zheng Zhang, Haofeng School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing China School of Engineering Newcastle University Newcastle upon Tyne United Kingdom Department of Computer Science Durham University Durham United Kingdom Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen China School of Artificial Intelligence Nanjing University of Science and Technology Jiangsu Nanjing China

Compositional Zero-shot Learning (CZSL) aims to identify novel compositions via known attribute-object pairs. The primary challenge in CZSL tasks lies in the significant discrepancies introduced by the complex interaction between the visual primitives of attribute and object, consequently decreasing the classification performance towards novel compositions. Previous remarkable works primarily addressed this issue by focusing on disentangling strategy or utilizing object-based conditional probabilities to constrain the selection space of attributes. Unfortunately, few studies have explored the problem from the perspective of modeling the mechanism of visual primitive interactions. Inspired by the success of vanilla adversarial learning in Cross-Domain Few-Shot Learning, we take a step further and devise a model-agnostic and Primitive-Based Adversarial training (PBadv) method to deal with this problem. Besides, the latest studies highlight the weakness of the perception of hard compositions even under data-balanced conditions. To this end, we propose a novel over-sampling strategy with object-similarity guidance to augment target compositional training data. We performed detailed quantitative analysis and retrieval experiments on well-established datasets, such as UT-Zappos50K, MIT-States, and C-GQA, to validate the effectiveness of our proposed method, and the state-of-the-art (SOTA) performance demonstrates the superiority of our approach. The code is available at https://***/lisuyi/PBadv_czsl. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

Balance Guided Incomplete Multi-View Spectral Clustering

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Sun, Lilei Wen, Jie Liu, Chengliang Fei, Lunke State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen Shenzhen518000 China School of Computer Science and Technology Guangdong University of Technology Guangzhou510000 China

There is a large amount of incomplete multi-view data in the real-world. How to cluster these incomplete multi-view data is an urgent realistic problem since almost all of the conventional multi-view clustering methods are inapplicable to the case with missing views. In this paper, we propose a new graph learning based incomplete multi-view clustering method to address this issue. Different from the existing works, our method seeks to learn a common consensus graph from all of the incomplete views and obtain a clustering indicator matrix in a unified framework. Specifically, to obtain a stable clustering result, a relaxed spectral clustering model is introduced to obtain a unique probability consensus representation whose all elements are positive to reflect the data clustering result. In view of the different contributions of views in the clustering task, we introduce a weighted multi-view learning mechanism to automatically balance their effects in the model optimization. In such a way, the intrinsic information in these incomplete multi-view data can be exploited sufficiently. The experimental results on several incomplete multi-view datasets illustrate that the proposed method achieves the best clustering performance among all of the compared state-of-the-art methods, which verifies the effectiveness of the proposed method for incomplete multi-view clustering. © 2022, The Authors. All rights reserved.

关键词： Cluster analysis