检索结果-内蒙古大学图书馆

2023 IEEE/CVF Conference on computer vision and pattern recognition Workshops, CVPRW 2023

作者： Phutke, Shruti S. Kulkarni, Ashutosh Vipparthi, Santosh Kumar Murala, Subrahmanyam Indian Institute of Technology Ropar Computer Vision and Pattern Recognition Lab Punjab Rupnagar India

ISBN: (纸本)9798350302493

Blind image inpainting is a crucial restoration task that does not demand additional mask information to restore the corrupted regions. Yet, it is a very less explored research area due to the difficulty in discriminating between corrupted and valid regions. There exist very few approaches for blind image inpainting which sometimes fail at producing plausible inpainted images. Since they follow a common practice of predicting the corrupted regions and then inpaint them. To skip the corrupted region prediction step and obtain better results, in this work, we propose a novel end-to-end architecture for blind image inpainting consisting of wavelet query multi-head attention transformer block and the omni-dimensional gated attention. The proposed wavelet query multi-head attention in the transformer block provides encoder features via processed wavelet coefficients as query to the multi-head attention. Further, the proposed omni-dimensional gated attention effectively provides all dimensional attentive features from the encoder to the respective decoder. Our proposed approach is compared numerically and visually with existing state-of-the-art methods for blind image inpainting on different standard datasets. The comparative and ablation studies prove the effectiveness of the proposed approach for blind image inpainting. The testing code is availab.e at : https://***/shrutiphutke/Blind-Omni-Wav-Net © 2023 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancement 20th

Bootstrap Diffusion Model Curve Estimation for High Resolut...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Huang, Jiancheng Liu, Yifan Chen, Shifeng ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819970247

Learning-based methods have attracted a lot of research attention and led to significant improvements in low-light image enhancement. However, most of them still suffer from two main problems: expensive computational cost in high resolution images and unsatisfactory performance in simultaneous enhancement and denoising. To address these problems, we propose BDCE, a bootstrap diffusion model that exploits the learning of the distribution of the curve parameters instead of the normal-light image itself. Specifically, we adopt the curve estimation method to handle the high-resolution images, where the curve parameters are estimated by our bootstrap diffusion model. In addition, a denoise module is applied in each iteration of curve adjustment to denoise the intermediate enhanced result of each iteration. We evaluate BDCE on commonly used benchmark datasets, and extensive experiments show that it achieves state-of-the-art qualitative and quantitative performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Dynamic Feature Queue for Surveillance Face Anti-spoofing via Progressive Training

Dynamic Feature Queue for Surveillance Face Anti-spoofing vi...

引用

2023 IEEE/CVF Conference on computer vision and pattern recognition Workshops, CVPRW 2023

作者： Wang, Keyao Huang, Mouxiao Zhang, Guosheng Yue, Haixiao Zhang, Gang Qiao, Yu China Chinese Academy of Sciences ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology China University of Chinese Academy of Sciences China

ISBN: (纸本)9798350302493

In recent years, face recognition systems have faced increasingly security threats, making it essential to employ Face Anti-spoofing (FAS) to protect against various types of attacks in traditional scenarios like phone unlocking, face payment and self-service security inspection. However, further exploration is required to fully secure FAS in long-distance settings. In this paper, we propose two contributions to enhance the security of face recognition systems: Dynamic Feature Queue (DFQ) and Progressive Training Strategy (PTS). DFQ converts the conventional binary classification task into a multi-classification task. It treats live samples as a closed set and attack samples as an open set by using a dynamic queue that stores the features of spoofing samples and updates them. On the other hand, PTS targets difficult samples and iteratively adds them in batches for training. The proposed PTS divides the entire training set into blocks, trains only a small portion of the data, and gradually increases the training data with each stage while also incorporating low-scoring positive samples and high-scoring spoof samples from the test set. These two contributions complement each other by enhancing the model's ability to generalize and defend against various types of attacks, making the face recognition system more secure and reliable. Our proposed methods have achieved top performance on ACER metric with 4.73% on the SuHiFiMask dataset [11] and won the first prize in Surveillance Face Anti-spoofing track of the Challenge@CVPR 2023. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Generalized Multimodal Fusion via Poisson-Nernst-Planck Equation

arXiv

引用

arXiv 2024年

作者： Xiong, Jiayu Wang, Jing Xiang, Hengjing Xue, Jun Xu, Chen Jiang, Zhouqiang Xiamen Key Lab of Computer Vision and Pattern Recognition Huaqiao University Xiamen China

Previous studies have highlighted significant advancements in multimodal fusion. Nevertheless, such methods often encounter challenges regarding the efficacy of feature extraction, data integrity, consistency of feature dimensions, and adaptability across various downstream tasks. This paper proposes a generalized multimodal fusion method (GMF) via the Poisson-Nernst-Planck (PNP) equation, which adeptly addresses the aforementioned issues. Theoretically, the optimization objective for traditional multimodal tasks is formulated and redefined by integrating information entropy and the flow of gradient backward step. Leveraging these theoretical insights, the PNP equation is applied to feature fusion, rethinking multimodal features through the framework of charged particles in physics and controlling their movement through dissociation, concentration, and reconstruction. Building on these theoretical foundations, GMF disassociated features which extracted by the unimodal feature extractor into modality-specific and modality-invariant subspaces, thereby reducing mutual information and subsequently lowering the entropy of downstream tasks. The identifiability of the feature’s origin enables our approach to function independently as a frontend, seamlessly integrated with a simple concatenation backend, or serve as a prerequisite for other modules. Experimental results on multiple downstream tasks show that the proposed GMF achieves performance close to the state-of-the-art (SOTA) accuracy while utilizing fewer parameters and computational resources. Furthermore, by integrating GMF with advanced fusion methods, we surpass the SOTA results. © 2024, CC BY-NC-SA.

关键词： Poisson equation

来源：评论

学校读者我要写书评

暂无评论

Generalist Segmentation Algorithm for Photoreceptors Analysis in Adaptive Optics Imaging 27th

Generalist Segmentation Algorithm for Photoreceptors Analys...

引用

27th International Conference on pattern recognition, ICPR 2024

作者： Kulyabin, Mikhail Sindel, Aline Pedersen, Hilde R. Gilson, Stuart Baraas, Rigmor Maier, Andreas Pattern Recognition Lab Department of Computer Science Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany National Centre for Optics Vision and Eye Care Faculty of Health and Social Sciences University of South-Eastern Norway Kongsberg Norway

ISBN: (纸本)9783031781032

Analyzing the cone photoreceptor pattern in images obtained from the living human retina using quantitative methods can be crucial for the early detection and management of various eye conditions. Confocal adaptive optics scanning light ophthalmoscope (AOSLO) imaging enables visualization of the cones from reflections of waveguiding cone photoreceptors. While there have been significant improvements in automated algorithms for segmenting cones in confocal AOSLO images, the process of lab.ling data remains lab.r-intensive and manual. This paper introduces a method based on deep learning (DL) for detecting and segmenting cones in AOSLO images. The models were trained on a semi-automatically lab.led dataset of 20 AOSLO batches of images of 18 participants for 0∘, 1∘, and 2∘ from the foveal center. F1 scores were 0.968, 0.958, and 0.954 for 0∘, 1∘, and 2∘, respectively, which is better than previously reported DL approaches. Our method minimizes the need for lab.led data by only necessitating a fraction of lab.led cones, which is especially beneficial in the field of ophthalmology, where lab.led data can often be limited. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

DarkGAN: Night Image Enhancement Using Generative Adversarial Networks 5th

DarkGAN: Night Image Enhancement Using Generative Adversaria...

引用

5th International Conference on computer vision and Image Processing, CVIP 2020

作者： Alaspure, Prasen Hambarde, Praful Dudhane, Akshay Murala, Subrahmanyam Computer Vision and Pattern Recognition Lab IIT Ropar Rupnagar India

ISBN: (纸本)9789811610851

Low light image enhancement is one of the challenging tasks in computer vision, and it becomes more difficult when images are very dark. Recently, most of low light image enhancement work is done either on synthetic data or on the images which are considerably visible. In this paper, we propose a method to enhance real-world night time images, which are dark and noisy. The proposed DarkGAN consists of two pairs of Generator - Discriminator. Moreover, the proposed network enhances dark shades and removes noise up to a much extent, with natural-looking colors in the output image. Experimental results evaluation of the proposed method on the "See In the Dark" dataset demonstrates the effectiveness of the proposed model compared with other state-of-the-art methods. The proposed method yields comparable better results on qualitative and quantitative assessments when compared with the existing methods. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Blind Image Inpainting via Omni-dimensional Gated Attention and Wavelet Queries

Blind Image Inpainting via Omni-dimensional Gated Attention ...

引用

IEEE computer Society Conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Shruti S. Phutke Ashutosh Kulkarni Santosh Kumar Vipparthi Subrahmanyam Murala Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar Rupnagar Punjab

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensemble and Personalized Transformer Models for Subject Identification and Relapse Detection in E-Prevention Challenge

Ensemble and Personalized Transformer Models for Subject Ide...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Salvatore Calcagno Raffaele Mineo Daniela Giordano Concetto Spampinato Department of Electrical Electronics and Computer Engineering Pattern Recognition and Computer Vision Laboratory (PeRCeiVe Lab) University of Catania Italy

In this short paper, we present the devised solutions for the subject identification and relapse detection tasks, which are part of the e-Prevention Challenge hosted at the ICASSP 2023 conference [1] [2] [3]. We specifically design an ensemble scheme of six models - five transformer-based ones and a CNN model - for the identification of subjects from wearable devices, while a personalized - one for each subject - scheme is used for relapse detection in psychotic disorder. Our final submitted solutions yield top performance on both tracks of the challenge: we ranked 2 nd on the subject identification task (with an accuracy of 93.85%) and 1 st on the relapse detection task (with a ROC-AUC and PR-AUC of about 0.65). Code and details are availab.e at https://***/perceivelab.e-prevention-icassp-2023.

关键词： Performance evaluation Codes Wearable computers Signal processing Transformers Acoustics Object recognition

来源：评论

学校读者我要写书评

暂无评论

Finding discriminative filters for specific degradations in blind super-resolution 21

Finding discriminative filters for specific degradations in ...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Liangbin Xie Xintao Wang Chao Dong Zhongang Qi Ying Shan Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences and ARC Lab Tencent PCG ARC Lab Tencent PCG Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences and Shanghai AI Laboratory Shanghai China

ISBN: (纸本)9781713845393

Recent blind super-resolution (SR) methods typically consist of two branches, one for degradation prediction and the other for conditional restoration. However, our experiments show that a one-branch network can achieve comparable performance to the two-branch scheme. Then we wonder: how can one-branch networks automatically learn to distinguish degradations? To find the answer, we propose a new diagnostic tool – Filter Attribution method based on Integral Gradient (FAIG). Unlike previous integral gradient methods, our FAIG aims at finding the most discriminative filters instead of input pixels/features for degradation removal in blind SR networks. With the discovered filters, we further develop a simple yet effective method to predict the degradation of an input image. Based on FAIG, we show that, in one-branch blind SR networks, 1) we are able to find a very small number of (1%) discriminative filters for each specific degradation; 2) The weights, locations and connections of the discovered filters are all important to determine the specific network function. 3) The task of degradation prediction can be implicitly realized by these discriminative filters without explicit supervised learning. Our findings can not only help us better understand network behaviors inside one-branch blind SR networks, but also provide guidance on designing more efficient architectures and diagnosing networks for blind SR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution Using Vast-Receptive-Field Attention 17th

Efficient Image Super-Resolution Using Vast-Receptive-Field ...

引用

17th European Conference on computer vision, ECCV 2022

作者： Zhou, Lin Cai, Haoming Gu, Jinjin Li, Zheyuan Liu, Yingqi Chen, Xiangyu Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Shanghai AI Laboratory Shanghai China The University of Sydney Sydney Australia University of Macau Zhuhai China

ISBN: (纸本)9783031250620

The attention mechanism plays a pivotal role in designing advanced super-resolution (SR) networks. In this work, we design an efficient SR network by improving the attention mechanism. We start from a simple pixel attention module and gradually modify it to achieve better super-resolution performance with reduced parameters. The specific approaches include: (1) increasing the receptive field of the attention branch, (2) replacing large dense convolution kernels with depthwise separable convolutions, and (3) introducing pixel normalization. These approaches paint a clear evolutionary roadmap for the design of attention mechanisms. Based on these observations, we propose VapSR, the Vast-receptive-field Pixel attention network. Experiments demonstrate the superior performance of VapSR. VapSR outperforms the present lightweight networks with even fewer parameters. And the light version of VapSR can use only 21.68% and 28.18% parameters of IMDB and RFDN to achieve similar performances to those networks. The code and models are availab.e at https://***/zhoumumu/VapSR. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

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：