检索结果-内蒙古大学图书馆

Survey on Deep Face Restoration: From Non-blind to Blind and Beyond

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Wenjie Wang, Mei Zhang, Kai Li, Juncheng Li, Xiaoming Zhang, Yuhang Gao, Guangwei Deng, Weihong Lin, Chia-Wen The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China The Computer Vision Lab ETH Zürich Zürich Switzerland The School of Communication and Information Engineering Shanghai University Shanghai China The Nanyang Technological University Singapore The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan

Face restoration (FR) is a specialized field within image restoration that aims to recover low-quality (LQ) face images into high-quality (HQ) face images. Recent advances in deep learning technology have led to significant progress in FR methods. In this paper, we begin by examining the prevalent factors responsible for real-world LQ images and introduce degradation techniques used to synthesize LQ images. We also discuss notable benchmarks commonly utilized in the field. Next, we categorize FR methods based on different tasks and explain their evolution over time. Furthermore, we explore the various facial priors commonly utilized in the restoration process and discuss strategies to enhance their effectiveness. In the experimental section, we thoroughly evaluate the performance of state-of-the-art FR methods across various tasks using a unified benchmark. We analyze their performance from different perspectives. Finally, we discuss the challenges faced in the field of FR and propose potential directions for future advancements. The open-source repository corresponding to this work can be found at https://***/24wenjie-li/Awesome-Face-Restoration. Copyright © 2023, The Authors. All rights reserved.

关键词： Restoration

Gray matter volume predicts individual body mass index and its development during adolescence 2021

学校读者我要写书评

暂无评论

Gray matter volume predicts individual body mass index and i...

13th International Conference on Bioinformatics and Biomedical Technology, ICBBT 2021

作者： Wang, Haiyan Jiang, Tianzi Brainnetome Center and National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation University of Electronic Science and Technology of China Chengdu625014 China Queensland Brain Institute University of Queensland BrisbaneQLD4072 Australia

ISBN: (纸本)9781450389655

Adolescent obesity is one of the most important current public health concerns, owing to its increased prevalence and adverse effects on physical and mental health. Body mass index (BMI) is a measure of obesity, and relationships between brain and BMI have been found based on univariate association analyses. However, whether/how neuroanatomical features can be used to predict the BMI and its development at the individual level during adolescence are unclear. Here, we analyzed the large-scale longitudinal IMAGEN dataset, in which structural magnetic resonance imaging and BMI were acquired at both 14 and 19 years old in the same subjects. Using the voxel-wise gray matter volume (GMV) as features and the multivariate machine learning method, we constructed predictive models for individually predicting the BMI at both 14 and 19 years old, as well as the longitudinal development of BMI between the 2 ages. We found that, the whole-brain GMV could predict the individual BMI at both 14 and 19 years old, and the development of GMV in cerebellum could predict the individual development of BMI. The contributing brain regions for predicting 14- and 19-year-old BMIs did not differ at a coarse scale, but exhibited considerable differences at a fine scale. Our results highlight the importance of GMV in predicting the individual cross-sectional BMI and its longitudinal development during adolescence. © 2021 ACM.

关键词： Forecasting

Lymphocyte Annotator: CD3+ and CD8+ IHC Stained Patch Image Annotation Tool

学校读者我要写书评

暂无评论

Lymphocyte Annotator: CD3+ and CD8+ IHC Stained Patch Image ...

Recent Advances in Electrical Engineering & Computer Sciences (RAEE & CS), International Symposium on

作者： Muhammad Mohsin Zafar Zunaira Rauf Anabia Sohail Asifullah Khan Pattern Recognition Lab DCIS Pakistan Institute of Engineering and Applied Sciences Islamabad Pakistan PIEAS Artificial Intelligence Center (PAIC) Pattern Recognition Lab DCIS Pakistan Institute of Engineering and Applied Sciences Islamabad Pakistan

ISBN: (数字)9780738131092

ISBN: (纸本)9781665415460

In digital pathology, preliminary step for the development of Computer Aided Diagnostics involves defining and labelling an Object of Interest. Contrary to traditional tiresome method of observation and marking of objects under microscope, digital pathology enables the use of annotation tools to capture localization information and morphology for targeted object(s). However, it is quite difficult to capture this information due to high inter and intra class variance. In this paper, we have addressed these two different problems by developing an easy to use and efficient tool "Lymphocyte Annotator" that allows a user to draw bounding box(es) on IHC stained images, and as a result, automatically generates multiple variants of segmentation masks for the targeted object. Lymphocyte Annotator provides multiple options for bounding box selection, with variation in bounding box size and type. The developed tool targets labelling of lymphocytes in histopathological images. This annotator generates five different types of masks by using a) Chan Vese Segmentation Model, b) Morphological Active Contours without Edges Model, c) Morphological Geodesic Active Contours Model, d) Adaptive Thresholding and e) Circular Masks, thus providing user with an opportunity to use a mixture of different types of generated masks. Capturing of lymphocytes' morphology using different models incorporates morphological variance and enables training of robust deep Convolutional Neural Network. The annotations created from this tool are by default exported in PASCAL VOC and JSON format. Lymphocyte annotator is an open-source tool, and can be accessed from source, available at https://***/m-mohsin-zafar/lysto_labeltool.

关键词： Tools Annotations Image segmentation Pathology labeling pattern recognition Task analysis

PC-HMR: Pose calibration for 3d human mesh recovery from 2D images/videos

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Luan, Tianyu Wang, Yali Zhang, Junhao Wang, Zhe Zhou, Zhipeng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China University of California Irvine United States

The end-to-end Human Mesh Recovery (HMR) approach (Kanazawa et al. 2018) has been successfully used for 3D body reconstruction. However, most HMR-based frameworks reconstruct human body by directly learning mesh parameters from images or videos, while lacking explicit guidance of 3D human pose in visual data. As a result, the generated mesh often exhibits incorrect pose for complex activities. To tackle this problem, we propose to exploit 3D pose to calibrate human mesh. Specifically, we develop two novel Pose Calibration frameworks, i.e., Serial PC-HMR and Parallel PC-HMR. By coupling advanced 3D pose estimators and HMR in a serial or parallel manner, these two frameworks can effectively correct human mesh with guidance of a concise pose calibration module. Furthermore, since the calibration module is designed via non-rigid pose transformation, our PCHMR frameworks can flexibly tackle bone length variations to alleviate misplacement in the calibrated mesh. Finally, our frameworks are based on generic and complementary integration of data-driven learning and geometrical modeling. Via plug-and-play modules, they can be efficiently adapted for both image/video-based human mesh recovery. Additionally, they have no requirement of extra 3D pose annotations in the testing phase, which releases inference difficulties in practice. We perform extensive experiments on the popular benchmarks, i.e., Human3.6M, 3DPW and SURREAL, where our PC-HMR frameworks achieve the SOTA results. Copyright © 2021, The Authors. All rights reserved.

关键词： Mesh generation

AutoCaption: Image captioning with neural architecture search

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhu, Xinxin Wang, Weining Guo, Longteng Liu, Jing National Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences China

Image captioning transforms complex visual information into abstract natural language for representation, which can help computers understanding the world quickly. However, due to the complexity of the real environment, it needs to identify key objects and realize their connections, and further generate natural language. The whole process involves an encoder module for visual understanding and a decoder module for language generation, which brings more challenges to the design of deep neural networks than other tasks. In this paper, we adopt a strategy of Network Architecture Search (NAS) to better design the RNN-based decoder module for image captioning automatically, called as AutoCaption. Specially, the reinforcement learning method based on shared parameters are explored to design the AutoCaption Model efficiently, and the search space includes connections between the layers and the operations in layers both in order to generate more architectures for the decoder. It is noted that RNN is equivalent to a subset of our search space. Experiments on the MSCOCO datasets show that our Auto-Caption model can achieve better performance than traditional hand-design methods. © 2020, CC BY.

关键词： Deep neural networks

Two-dimensional multi-fiber spectrum image correction based on machine learning techniques

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xu, Jiali Yin, Qian Guo, Ping Zheng, Xin Image Processing and Pattern Recognition Lab. School of Artificial Intelligence Beijing Normal University Beijing100875 China Image Processing and Pattern Recognition Lab School of Systems Science Beijing Normal University Beijing100875 China

Due to limited size and imperfect of the optical components in a spectrometer, aberration has inevitably been brought into two-dimensional multi-fiber spectrum image in LAMOST, which leads to obvious spacial variation of the point spread functions (PSFs). Consequently, if spatial variant PSFs are estimated directly, the huge storage and intensive computation requirements result in deconvolutional spectral extraction method become intractable. In this paper, we proposed a novel method to solve the problem of spatial variation PSF through image aberration correction. When CCD image aberration is corrected, PSF, the convolution kernel, can be approximated by one spatial invariant PSF only. Specifically, machine learning techniques are adopted to calibrate distorted spectral image, including Total Least Squares (TLS) algorithm, intelligent sampling method, multi-layer feed-forward neural networks. The calibration experiments on the LAMOST CCD images show that the calibration effect of proposed method is effectible. At the same time, the spectrum extraction results before and after calibration are compared, results show the characteristics of the extracted one-dimensional waveform are more close to an ideal optics system, and the PSF of the corrected object spectrum image estimated by the blind deconvolution method is nearly central symmetry, which indicates that our proposed method can significantly reduce the complexity of spectrum extraction and improve extraction accuracy. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical transfer function

Investigate indistinguishable points in semantic segmentation of 3D point cloud

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xu, Mingye Zhou, Zhipeng Zhang, Junhao Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China Shanghai AI Lab Shanghai China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

This paper investigates the indistinguishable points (difficult to predict label) in semantic segmentation for large-scale 3D point clouds. The indistinguishable points consist of those located in complex boundary, points with similar local textures but different categories, and points in isolate small hard areas, which largely harm the performance of 3D semantic segmentation. To address this challenge, we propose a novel Indistinguishable Area Focalization Network (IAF-Net), which selects indistinguishable points adaptively by utilizing the hierarchical semantic features and enhance fine-grained features for points especially those indistinguishable points. We also introduce multi-stage loss to improve the feature representation in a progressive way. Moreover, in order to analyze the segmentation performances of indistinguishable areas, we propose a new evaluation metric called Indistinguishable Points Based Metric (IPBM). Our IAF-Net achieves the comparable results with state-of-the-art performance on several popular 3D point cloud datasets e.g. S3DIS and ScanNet, and clearly outperforms other methods on IPBM. Our code will be available at https://***/MingyeXu/IAF-Net. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

TR-BERT: Dynamic token reduction for accelerating BERT inference

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ye, Deming Lin, Yankai Huang, Yufei Sun, Maosong Department of Computer Science and Technology Tsinghua University Beijing China Institute for Artificial Intelligence Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology China State Key Lab on Intelligent Technology and Systems Tsinghua University Beijing China Beijing Academy of Artificial Intelligence China Pattern Recognition Center WeChat AI Tencent Inc

Existing pre-trained language models (PLMs) are often computationally expensive in inference, making them impractical in various resource-limited real-world applications. To address this issue, we propose a dynamic token reduction approach to accelerate PLMs' inference, named TR-BERT, which could flexibly adapt the layer number of each token in inference to avoid redundant calculation. Specially, TR-BERT formulates the token reduction process as a multi-step token selection problem and automatically learns the selection strategy via reinforcement learning. The experimental results on several downstream NLP tasks show that TR-BERT is able to speed up BERT by 2-5 times to satisfy various performance demands. Moreover, TR-BERT can also achieve better performance with less computation in a suite of long-text tasks since its token-level layer number adaption greatly accelerates the self-attention operation in PLMs. The source code and experiment details of this paper can be obtained from https://***/thunlp/TR-BERT. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

CB-HVTNet: A channel-boosted hybrid vision transformer network for lymphocyte assessment in histopathological images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ali, Momina Liaqat Rauf, Zunaira Khan, Asifullah Sohail, Anabia Ullah, Rafi Gwak, Jeonghwan Pattern Recognition Lab Department of Computer & Information Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Center for Mathematical Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Department of Computer Science Faculty of Computing and Artificial Intelligence Air University IslamabadE-9 Pakistan Perak31750 Malaysia Department of Software Korea National University of Transportation Chungju27469 Korea Republic of

Transformers, due to their ability to learn long-range dependencies, have overcome the shortcomings of convolutional neural networks (CNNs) for global perspective learning. However, their multi-head attention module only captures global-level feature representations, which is insufficient for medical images. To address this issue, we propose a Channel Boosted Hybrid Vision Transformer (CB-HVT) that uses transfer learning to generate boosted channels and employs both transformers and CNNs to analyse lymphocytes in histopathological images. The proposed CB-HVT comprises five modules to effectively identify lymphocytes. Its (i) channel generation module, uses the idea of channel boosting through transfer learning to extract diverse channels from different auxiliary learners. These boosted channels are first concatenated and ranked using an attention mechanism in the (ii) channel exploitation module. A fusion block is then utilized in the (iii) channel merging module for a gradual and systematic merging of the diverse boosted channels to improve the network’s learning representations. The CB-HVT also employs a proposal network in its (iv) region aware module followed by its (v) detection and segmentation head to accurately identify and distinguish objects, even in the regions with crowded presence and artifacts. We evaluated the proposed CB-HVT on two publicly available datasets for lymphocyte assessment in histopathological images. The results demonstrate that CB-HVT has a good generalization on unseen data therefore, it can serve as a valuable tool for pathologists. Copyright © 2023, The Authors. All rights reserved.

关键词： Lymphocytes