检索结果-内蒙古大学图书馆

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Huang, Chang-Ti Chen, Jun-Cheng Wu, Ja-Ling Natl Taiwan Univ Taipei Taiwan Acad Sinica Taipei Taiwan

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193601

L-0-norm regularization is one of the most efficient approaches to learn a sparse neural network. Due to its discrete nature, differentiable and approximate regularizations based on the concrete distribution [31] or its variants are proposed as alternatives;however, the concrete relaxation suffers from high-variance gradient estimates and is limited to its own concrete distribution. To address these issues, in this paper, we propose a more general framework for relaxing binary gates through mixture distributions. With the proposed method, any mixture pair of distributions converging to delta(0) and delta(1) can be applied to construct smoothed binary gates. We further introduce a reparameterization method for the smoothed binary gates drawn from mixture distributions to enable efficient gradient gradient-based optimization under the proposed deep learning algorithm. Extensive experiments are conducted, and the results show that the proposed approach achieves better performance in terms of pruned architectures, structured sparsity and the reduced number of floating point operations (FLOPs) as compared with other state-of-the-art sparsity-inducing methods.

关键词： Logic gates Training Neurons computer architecture Artificial neural networks Computational modeling Exponential distribution

来源：评论

学校读者我要写书评

暂无评论

Equiangular Basis Vectors

Equiangular Basis Vectors

引用

conference on computer vision and pattern recognition (CVPR)

作者： Yang Shen Xuhao Sun Xiu-Shen Wei School of Computer Science and Engineering Nanjing University of Science and Technology China

We propose Equiangular Basis Vectors (EBVs) for classification tasks. In deep neural networks, models usually end with a k-way fully connected layer with softmax to handle different classification tasks. The learning objective of these methods can be summarized as mapping the learned feature representations to the samples' label space. While in metric learning approaches, the main objective is to learn a transformation function that maps training data points from the original space to a new space where similar points are closer while dissimilar points become farther apart. Different from previous methods, our EBVs generate normalized vector embeddings as “predefined classifiers” which are required to not only be with the equal status between each other, but also be as orthogonal as possible. By minimizing the spherical distance of the embedding of an input between its categorical EBV in training, the predictions can be obtained by identifying the categorical EBV with the smallest distance during inference. Various experiments on the ImageNet-1K dataset and other downstream tasks demonstrate that our method outperforms the general fully connected classifier while it does not introduce huge additional computation compared with classical metric learning methods. Our EBVs won the first place in the 2022 DIGIX Global AI Challenge, and our code is open-source and available at https://***/NJUST-VIPGroup/Equiangular-Basis-Vectors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised domain adaptation and super resolution on drone images for autonomous dry herbage biomass estimation

Unsupervised domain adaptation and super resolution on drone...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Paul Albert Mohamed Saadeldin Badri Narayanan Brian Mac Namee Deirdre Hennessy Noel E. O’ Connor Kevin McGuinness School of Electronic Engineering Dublin City University Insight Centre for Data Analytics VistaMilk School of Computer Science University College Dublin Teagasc

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487405

Herbage mass yield and composition estimation is an important tool for dairy farmers to ensure an adequate supply of high quality herbage for grazing and subsequently milk production. By accurately estimating herbage mass and composition, targeted nitrogen fertiliser application strategies can be deployed to improve localised regions in a herbage field, effectively reducing the negative impacts of over-fertilization on biodiversity and the environment. In this context, deep learning algorithms offer a tempting alternative to the usual means of sward composition estimation, which involves the destructive process of cutting a sample from the herbage field and sorting by hand all plant species in the herbage. The process is labour intensive and time consuming and so not utilised by farmers. Deep learning has been successfully applied in this context on images collected by high-resolution cameras on the ground. Moving the deep learning solution to drone imaging, however, has the potential to further improve the herbage mass yield and composition estimation task by extending the ground-level estimation to the large surfaces occupied by fields/paddocks. Drone images come at the cost of lower resolution views of the fields taken from a high altitude and requires further herbage ground-truth collection from the large surfaces covered by drone images. This paper proposes to transfer knowledge learned on ground-level images to raw drone images in an unsupervised manner. To do so, we use unpaired image style translation to enhance the resolution of drone images by a factor of eight and modify them to appear closer to their ground-level counterparts. We then use the enhanced drone images to train a semi-supervised algorithm that uses ground-truthed, ground-level images as the labelled data together with a large amount of unlabeled drone images. We validate our results on a small held-out drone image test set to show the validity of our approach, which opens the way for automate

关键词： Deep learning computer vision Image resolution Costs Estimation Prediction algorithms Cameras

来源：评论

学校读者我要写书评

暂无评论

Hippocampus substructure segmentation using morphological vision transformer learning

引用

PHYSICS IN MEDICINE AND BIOLOGY 2023年第23期68卷 235013-235013页

作者： Lei, Yang Ding, Yifu Qiu, Richard L. J. Wang, Tonghe Roper, Justin Fu, Yabo Shu, Hui-Kuo Mao, Hui Yang, Xiaofeng Emory Univ Dept Radiat Oncol Atlanta GA 30308 USA Emory Univ Winship Canc Inst Atlanta GA 30308 USA Mem Sloan Kettering Canc Ctr Dept Med Phys New York NY 10065 USA Dept Radiol & Imaging Sci Atlanta GA 30308 USA Winship Canc Inst Atlanta GA 30308 USA

The hippocampus plays a crucial role in memory and cognition. Because of the associated toxicity from whole brain radiotherapy, more advanced treatment planning techniques prioritize hippocampal avoidance, which depends on an accurate segmentation of the small and complexly shaped hippocampus. To achieve accurate segmentation of the anterior and posterior regions of the hippocampus from T1 weighted (T1w) MR images, we developed a novel model, Hippo-Net, which uses a cascaded model strategy. The proposed model consists of two major parts: (1) a localization model is used to detect the volume-of-interest (VOI) of hippocampus. (2) An end-to-end morphological vision transformer network (Franchi et al 2020 pattern Recognit. 102 107246, Ranem et al 2022 ieee/cvf Conf. on computer vision and pattern recognition workshops (cvprw) pp 3710-3719) is used to perform substructures segmentation within the hippocampus VOI. The substructures include the anterior and posterior regions of the hippocampus, which are defined as the hippocampus proper and parts of the subiculum. The vision transformer incorporates the dominant features extracted from MR images, which are further improved by learning-based morphological operators. The integration of these morphological operators into the vision transformer increases the accuracy and ability to separate hippocampus structure into its two distinct substructures. A total of 260 T1w MRI datasets from medical segmentation decathlon dataset were used in this study. We conducted a five-fold cross-validation on the first 200 T1w MR images and then performed a hold-out test on the remaining 60 T1w MR images with the model trained on the first 200 images. In five-fold cross-validation, the Dice similarity coefficients were 0.900 +/- 0.029 and 0.886 +/- 0.031 for the hippocampus proper and parts of the subiculum, respectively. The mean surface distances (MSDs) were 0.426 +/- 0.115 mm and 0.401 +/- 0.100 mm for the hippocampus proper and parts of th

关键词： hippocampus substructure segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

Thermal Image Super-Resolution Challenge - PBVS 2020

Thermal Image Super-Resolution Challenge - PBVS 2020

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Rivadeneira, Rafael E. Sappa, Angel D. Vintimilla, Boris X. Guo, Lin Hou, Jiankun Mehri, Armin Behjati Ardakani, Parichehr Patel, Heena Chudasama, Vishal Prajapati, Kalpesh Upla, Kishor P. Ramachandra, Raghavendra Raja, Kiran Busch, Christoph Almasri, Feras Debeir, Olivier Nathan, Sabari Kansal, Priya Gutierrez, Nolan Mojra, Bardia Beksi, William J. ESPOL Escuela Super Politecn Litoral CIDIS Fac Ingn Elect & Comp 30-5 Via PerimetralPOB 09-01-5863 Guayaquil Ecuador Comp Vis Ctr Campus UAB Barcelona 08193 Spain Oklahoma State Univ Stillwater OK 74078 USA SVNIT Surat India NTNU Gjovik Norway Univ Libre Bruxelles Brussels Belgium Couger Inc Tokyo Japan Univ Texas Arlington Dept Comp Sci & Engn Robot Vis Lab Arlington TX 76019 USA

ISBN: (纸本)9781728193601

This paper summarizes the top contributions to the first challenge on thermal image super-resolution (TISR), which was organized as part of the Perception Beyond the Visible Spectrum (PBVS) 2020 workshop. In this challenge, a novel thermal image dataset is considered together with state-of-the-art approaches evaluated under a common framework. The dataset used in the challenge consists of 1021 thermal images, obtained from three distinct thermal cameras at different resolutions (low-resolution, mid-resolution, and high-resolution), resulting in a total of 3063 thermal images. From each resolution, 951 images are used for training and 50 for testing while the 20 remaining images are used for two proposed evaluations. The first evaluation consists of downsampling the low-resolution, mid-resolution, and high-resolution thermal images by x2, x3 and x4 respectively, and comparing their super-resolution results with the corresponding ground truth images. The second evaluation is comprised of obtaining the x2 super-resolution from a given mid-resolution thermal image and comparing it with the corresponding semi-registered high-resolution thermal image. Out of 51 registered participants, 6 teams reached the final validation phase.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Finetune like you pretrain: Improved finetuning of zero-shot vision models

Finetune like you pretrain: Improved finetuning of zero-shot...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Sachin Goyal Ananya Kumar Sankalp Garg Zico Kolter Aditi Raghunathan Carnegie Mellon University Stanford University Bosch Center for AI

Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works (Kumar et al., 2022; Wortsman et al., 2021) have shown that even subtle differences in the finetuning process can lead to surprisingly large differences in the final performance, both for in-distribution (ID) and out-of-distribution (OOD) data. In this work, we show that a natural and simple approach of mimicking contrastive pretraining consistently outperforms alternative finetuning approaches. Specifically, we cast downstream class labels as text prompts and continue optimizing the contrastive loss between image embeddings and class-descriptive prompt embeddings (contrastive finetuning). Our method consistently outperforms baselines across 7 distribution shift, 6 transfer learning, and 3 few-shot learning benchmarks. On WILDS-iWILDCam, our proposed approach FLYP outperforms the top of the leaderboard by 2.3% ID and 2.7% OOD, giving the highest reported accuracy. Averaged across 7 OOD datasets (2 WILDS and 5 ImageNet associated shifts), FLYP gives gains of 4.2% OOD over standard finetuning and outperforms current state-of-the-art (LP-FT) by more than 1 % both ID and OOD. Similarly, on 3 few-shot learning benchmarks, FLYP gives gains up to 4.6% over standard finetuning and 4.4% over the state-of-the-art. Thus we establish our proposed method of contrastive finetuning as a simple and intuitive state-of-the-art for supervised finetuning of image-text models like CLIP. Code is available at https://***/locuslab/FLYP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results

NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods ...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Eduardo Pé rez-Pellitero Sibi Catley-Chandar Richard Shaw Aleš Leonardis Radu Timofte Zexin Zhang Cen Liu Yunbo Peng Yue Lin Gaocheng Yu Jin Zhang Zhe Ma Hongbin Wang Xiangyu Chen Xintao Wang Haiwei Wu Lin Liu Chao Dong Jiantao Zhou Qingsen Yan Song Zhang Weiye Chen Yuhang Liu Zhen Zhang Yanning Zhang Javen Qinfeng Shi Dong Gong Dan Zhu Mengdi Sun Guannan Chen Yang Hu Haowei Li Baozhu Zou Zhen Liu Wenjie Lin Ting Jiang Chengzhi Jiang Xinpeng Li Mingyan Han Haoqiang Fan Jian Sun Shuaicheng Liu Juan Marí n-Vega Michael Sloth Peter Schneider-Kamp Richard Rö ttger Chunyang Li Long Bao Gang He Ziyao Xu Li Xu Gen Zhan Ming Sun Xing Wen Junlin Li Jinjing Li Chenghua Li Ruipeng Gang Fangya Li Chenming Liu Shuang Feng Fei Lei Rui Liu Junxiang Ruan Tianhong Dai Wei Li Zhan Lu Hengyan Liu Peian Huang Guangyu Ren Yonglin Luo Chang Liu Qiang Tu Sai Ma Yizhen Cao Steven Tel Barthelemy Heyrman Dominique Ginhac Chul Lee Gahyeon Kim Seonghyun Park An Gia Vien Truong Thanh Nhat Mai Howoon Yoon Tu Vo Alexander Holston Sheir Zaheer Chan Y. Park Huawei Noah&#x2019 s Ark Laboratory ETH Z&#x00FC rich University of W&#x00FC rzburg

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487405

This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022. This manuscript focuses on the competition set-up, datasets, the proposed methods and their results. The challenge aims at estimating an HDR image from multiple respective low dynamic range (LDR) observations, which might suffer from under-or over-exposed regions and different sources of noise. The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i.e. solutions can not exceed a given number of operations). In Track 2, participants are asked to minimize the complexity of their solutions while imposing a constraint on fidelity scores (i.e. solutions are required to obtain a higher fidelity score than the prescribed baseline). Both tracks use the same data and metrics: Fidelity is measured by means of PSNR with respect to a ground-truth HDR image (computed both directly and with a canonical tonemapping operation), while complexity metrics include the number of Multiply-Accumulate (MAC) operations and runtime (in seconds).

关键词： computer vision Runtime conferences Imaging Dynamic range Particle measurements Market research

来源：评论

学校读者我要写书评

暂无评论

Virtual Immunohistochemistry Staining for Histological Images Assisted by Weakly-supervised Learning

Virtual Immunohistochemistry Staining for Histological Image...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Jiahan Li Jiuyang Dong Shenjin Huang Xi Li Junjun Jiang Xiaopeng Fan Yongbing Zhang Harbin Institute of Technology Department of Gastroenterology Peking University Shenzhen Hospital Harbin Institute of Technology Shenzhen

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Recently, virtual staining technology has greatly promoted the advancement of histopathology. Despite the practical successes achieved, the outstanding performance of most virtual staining methods relies on hard-to-obtain paired images in training. In this paper, we propose a method for virtual immunohistochemistry (IHC) staining, named confusion-GAN, which does not require paired images and can achieve comparable performance to supervised algorithms. Specifically, we propose a multi-branch discriminator, which judges if the features of generated images can be embedded into the feature pool of target domain images, to improve the visual quality of generated images. Meanwhile, we also propose a novel patch-level pathology information extractor, which is assisted by multiple instance learning, to ensure pathological consistency during virtual staining. Extensive experiments were conducted on three types of IHC images, including a high-resolution hepatocel-lular carcinoma immunohistochemical dataset proposed by us. The results demonstrated that our proposed confusion-GAN can generate highly realistic images that are capable of deceiving even experienced pathologists. Furthermore, compared to using H&E images directly, the downstream diagnosis achieved higher accuracy when using images generated by confusion-GAN. Our dataset and codes will be available at https://***/jiahanli2022/confusion-GAN.

关键词： Training Visualization computer vision Accuracy Codes Image synthesis Histopathology

来源：评论

学校读者我要写书评

暂无评论

An Iterative Quantum Approach for Transformation Estimation from Point Sets

An Iterative Quantum Approach for Transformation Estimation ...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Natacha Luete Meli Florian Mannel Jan Lellmann Institute of Mathematics and Image Computing University of Luebeck

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469470

We propose an iterative method for estimating rigid transformations from point sets using adiabatic quantum computation. Compared to existing quantum approaches, our method relies on an adaptive scheme to solve the problem to high precision, and does not suffer from inconsistent rotation matrices. Experimentally, our method performs robustly on several 2D and 3D datasets even with high outlier ratio.

关键词： computer vision Three-dimensional displays Annealing Estimation Quantum annealing pattern recognition Iterative methods

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2021 Challenge for Defocus Deblurring Using Dual-pixel Images: Methods and Results

NTIRE 2021 Challenge for Defocus Deblurring Using Dual-pixel...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Abdullah Abuolaim Radu Timofte Michael S. Brown Dafeng Zhang Xiaobing Wang Syed Waqas Zamir Aditya Arora Salman Khan Munawar Hayat Fahad Shahbaz Khan Ling Shao Shuai Liu Lei Lei Chaoyu Feng Zhiwei Xiong Zeyu Xiao Ruikang Xu Yunan Zhu Dong Liu Tu Vo Si Miao Nisarg A. Shah Pengwei Liang Zhiwei Zhong Xingyu Hu Yiqun Chen Chenghua Li Xiaoying Bai Chi Zhang Yiheng Yao Ruipeng Gang Sabari Nathan Thangavelu Ragavendran Venkatakrishnan Srinija Venkatakrishnan Srivatsav York University ETH Zurich The organizers of the NTIRE 2021 defocus deblurring challenge

ISBN: (纸本)9781665449007

This paper provides a review of the NTIRE 2021 challenge targeting defocus deblurring using dual-pixel (DP) data. The goal of this single-track challenge was to reduce spatially varying defocus blur present in images captured with a shallow depth of field. The images used in this challenge were obtained using a DP sensor that provided a pair of DP views per captured image. Submitted solutions were evaluated using conventional signal processing metrics, namely peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). Out of 185 registered participants, nine teams provided methods and competed in the final stage. The paper describes the methods proposed by the participating teams and their results. The winning teams represent the state-of-the-art in terms of defocus de-blurring using DP images.

关键词： computer vision PSNR Atmospheric measurements conferences Signal processing Particle measurements pattern recognition

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：