检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Li, Xiang Hu, Xiaolin Yang, Jian Pca Lab Key Lab of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Momenta Department of Computer Science and Technology Tsinghua University

The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic subfeatures. These sub-features can usually be distributed in grouped form in the feature vector of each layer [43, 32], representing various semantic entities. However, the activation of these sub-features is often spatially affected by similar patterns and noisy backgrounds, resulting in erroneous localization and identification. We propose a Spatial Group-wise Enhance (SGE) module that can adjust the importance of each sub-feature by generating an attention factor for each spatial location in each semantic group, so that every individual group can autonomously enhance its learnt expression and suppress possible noise. The attention factors are only guided by the similarities between the global and local feature descriptors inside each group, thus the design of SGE module is extremely lightweight with almost no extra parameters and calculations. Despite being trained with only category supervisions, the SGE component is extremely effective in highlighting multiple active areas with various high-order semantics (such as the dog's eyes, nose, etc.). When integrated with popular CNN backbones, SGE can significantly boost the performance of image recognition tasks. Specifically, based on ResNet50 backbones, SGE achieves 1.2% Top-1 accuracy improvement on the imageNet benchmark and 1.0∼2.0% AP gain on the COCO benchmark across a wide range of detectors (Faster/Mask/Cascade RCNN and RetinaNet). Codes and pretrained models are available at https://***/implus/PytorchInsight. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challenge Report

Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challen...

引用

2023 IEEE/CVF Conference on computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Conde, Marcos V. Kolmet, Manuel Seizinger, Tim Bishop, Tom E. Timofte, Radu Kong, Xiangyu Zhang, Dafeng Wu, Jinlong Wang, Fan Peng, Juewen Pan, Zhiyu Liu, Chengxin Luo, Xianrui Sun, Huiqiang Shen, Liao Cao, Zhiguo Xian, Ke Liu, Chaowei Chen, Zigeng Yang, Xingyi Liu, Songhua Jing, Yongcheng Mi, Michael Bi Wang, Xinchao Yang, Zhihao Lian, Wenyi Lai, Siyuan Zhang, Haichuan Hoang, Trung Yazdani, Amirsaeed Monga, Vishal Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjölund, Jens Schön, Thomas B. Zhao, Yuxuan Chen, Baoliang Xu, Yiqing Niu, Jixiang Computer Vision Lab CAIDAS IFI University of Würzburg Germany Glass Imaging Inc. China Huazhong University of Science and Technology China Nanyang Technological University Singapore National University of Singapore Singapore University of Sydney Australia Huawei Uppsala University Sweden Department of Electrical Engineering Pennsylvania State University United States Department of Information Technology Uppsala University Sweden Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education Xidian University Xi'an China North China University of Technology China

ISBN: (纸本)9798350302493

We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge. Recent advancements of mobile photography aim to reach the visual quality of full-frame cameras. Now, a goal in computational photography is to optimize the Bokeh effect itself, which is the aesthetic quality of the blur in out-of-focus areas of an image. Photographers create this aesthetic effect by benefiting from the lens optical *** aim of this work is to design a neural network capable of converting the the Bokeh effect of one lens to the effect of another lens without harming the sharp foreground regions in the image. For a given input image, knowing the target lens type, we render or transform the Bokeh effect accordingly to the lens properties. We build the BETD using two full-frame Sony cameras, and diverse lens *** the best of our knowledge, we are the first attempt to solve this novel task, and we provide the first BETD dataset and benchmark for it. The challenge had 99 registered participants. The submitted methods gauge the state-of-the-art in Bokeh effect rendering and transformation. © 2023 IEEE.

关键词： Color photography

来源：评论

学校读者我要写书评

暂无评论

Fast and light-weight network for single frame structured illumination microscopy super-resolution

arXiv

引用

arXiv 2021年

作者： Cheng, Xi Li, Jun Dai, Qiang Fu, Zhenyong Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Technology Soochow University Suzhou China

Structured illumination microscopy (SIM) is an important super-resolution based microscopy technique that breaks the diffraction limit and enhances optical microscopy systems. With the development of biology and medical engineering, there is a high demand for real-time and robust SIM imaging under extreme low light and short exposure environments. Existing SIM techniques typically require multiple structured illumination frames to produce a high-resolution image. In this paper, we propose a single-frame structured illumination microscopy (SF-SIM) based on deep learning. Our SF-SIM only needs one shot of a structured illumination frame and generates similar results compared with the traditional SIM systems that typically require 15 shots. In our SF-SIM, we propose a noise estimator which can effectively suppress the noise in the image and enable our method to work under the low light and short exposure environment, without the need for stacking multiple frames for non-local denoising. We also design a bandpass attention module that makes our deep network more sensitive to the change of frequency and enhances the imaging quality. Our proposed SF-SIM is almost 14 times faster than traditional SIM methods when achieving similar results. Therefore, our method is significantly valuable for the development of microbiology and medicine. © 2021, CC BY-NC-SA.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Methods for Ship Classification: From Visible to Infrared images 5

Deep Learning Methods for Ship Classification: From Visible ...

引用

5th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2023

作者： Liu, Tianci Qin, Hengjia Zhan, Zhuo Liu, Yunpeng Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China Chinese Academy of Sciences Key Laboratory of Opto-Electronic Information Processing Shenyang110016 China Key Laboratory of Image Understanding and Computer Vision Liaoning Province Shenyang110016 China The Third Military Representative Office of the Air Force Equipment Department in Shenyang Region Liaoning Province Shenyang110027 China

ISBN: (纸本)9798350357950

Deep learning methods have achieved excellent performances on visual tasks of target recognition and classification. The rapid development of autonomous seafaring vessels comes up with the requirement to recognize other maritime ships day and night. However, the recognition of ships based on the deep neural networks may not always access the results as expectation when the ships are under the nighttime environment. To this issue, we consider the ship recognition task under the deep learning framework with paired visible images and infrared images. In this article, we propose an end-to-end convolutional network based on visible images and infrared images of the autonomous seafaring vessels. To demonstrate the effectiveness of our model, we choose the V AIS dataset to test the performance of classifying the maritime ships. Experimental results show that the proposed network outperforms the state-of-the-art methods based on the V AIS database. © 2023 IEEE.

关键词： deep learning infrared images neural network Ship recognition

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization

引用

IEEE transactions on pattern analysis and machine intelligence 2020年第7期42卷 1654-1669页

作者： Yu Chen Chunhua Shen Hao Chen Xiu-Shen Wei Lingqiao Liu Jian Yang Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security Nanjing University of Science and Technology Nanjing Jiangsu China School of Computer Science The University of Adelaide Adelaide SA Australia Megvii Research Nanjing Megvii Technology Nanjing Jiangsu China

Landmark/pose estimation in single monocular images has received much effort in computer vision due to its important applications. It remains a challenging task when input images come with severe occlusions caused by, e.g., adverse camera views. Under such circumstances, biologically implausible pose predictions may be produced. In contrast, human vision is able to predict poses by exploiting geometric constraints of landmark point inter-connectivity. To address the problem, by incorporating priors about the structure of pose components, we propose a novel structure-aware fully convolutional network to implicitly take such priors into account during training of the deep network. Explicit learning of such constraints is typically challenging. Instead, inspired by how human identifies implausible poses, we design discriminators to distinguish the real poses from the fake ones (such as biologically implausible ones). If the pose generator G generates results that the discriminator fails to distinguish from real ones, the network successfully learns the priors. Training of the network follows the strategy of conditional Generative Adversarial Networks (GANs). The effectiveness of the proposed network is evaluated on three pose-related tasks: 2D human pose estimation, 2D facial landmark estimation and 3D human pose estimation. The proposed approach significantly outperforms several state-of-the-art methods and almost always generates plausible pose predictions, demonstrating the usefulness of implicit learning of structures using GANs.

关键词： computer vision Face Recognition Learning Artificial Intelligence Neural Nets Pose Estimation Landmark Localization computer vision Geometric Constraints Landmark Point Inter Connectivity Conditional Generative Adversarial Networks 2 D Facial Landmark Estimation Pose Predictions Structure Aware Fully Convolutional Network 3 D Human Pose Estimation 2 D Human Pose Estimation Pose Estimation Two Dimensional Displays Three Dimensional Displays Heating Systems Task Analysis Training Pose Estimation Landmark Localization Structure Aware Network Adversarial Training Multi Task Learning Deep Convolutional Networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive and Background-Aware Match for Class-Agnostic Counting

SSRN

引用

SSRN 2023年

作者： Gong, Shenjian Yang, Jian Zhang, Shanshan PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Nankai University China

Class-agnostic counting (CAC) aims to count object instances in an image by simply specifying a few exemplar boxes of interest. The key challenge for CAC is how to tailor a desirable interaction between exemplar and query features. Previous CAC methods implement such interaction by solely leveraging standard global feature convolution. We find this interaction leads to under-match caused by intra-class diversity and over-match on background, which severely degrades counting performance. In this work, we propose a novel feature interaction method called Adaptive and Background-Aware Match (ABM) against high intra-class diversity and noisy background. Concretely, given exemplar and query features, we improve the original high-dimensional coupled space match to adaptive orthogonal subspace match (AOM), avoiding under-match caused by intra-class diversity. Moreover, background-specific match (BSM) employs interaction between learnable background prototype and query feature to provide global background priors, making match be aware of background regions. Additionally, we find the high scale variance among different query images leads to bad counting performance for extremely small scale objects. Object scale unify (OSU) is proposed to take the size of the exemplars as the scale prior and resize query images such that all objects are in a uniform average scale. Extensive experiments on FSC-147 show that our method outperforms state-of-the-art approaches. We also conduct extensive ablation studies to demonstrate the effectiveness of each component of our proposed method. The code is publicly available at https://***/Yankeegsj/ABMNet. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Selective kernel networks

arXiv

引用

arXiv 2019年

作者： Li, Xiang Wang, Wenhai Hu, Xiaolin Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China Momenta National Key Lab for Novel Software Technology Nanjing University Department of Computer Science and Technology Tsinghua University China

In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscience community that the receptive field size of visual cortical neurons are modulated by the stimulus, which has been rarely considered in constructing CNNs. We propose a dynamic selection mechanism in CNNs that allows each neuron to adaptively adjust its receptive field size based on multiple scales of input information. A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer. Multiple SK units are stacked to a deep network termed Selective Kernel Networks (SKNets). On the imageNet and CIFAR benchmarks, we empirically show that SKNet outperforms the existing state-of-the-art architectures with lower model complexity. Detailed analyses show that the neurons in SKNet can capture target objects with different scales, which verifies the capability of neurons for adaptively adjusting their receptive field sizes according to the input. The code and models are available at https://***/implus/SKNet. Copyright © 2019, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Norm-Aware Embedding for Efficient Person Search

Norm-Aware Embedding for Efficient Person Search

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Di Chen Shanshan Zhang Jian Yang Bernt Schiele PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Max Planck Institute for Informatics Saarland Informatics Campus Jiangsu Key Lab of Image and Video Understanding for Social Security

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Person Search is a practically relevant task that aims to jointly solve Person Detection and Person Re-identification (re-ID). Specifically, it requires to find and locate all instances with the same identity as the query person in a set of panoramic gallery images. One major challenge comes from the contradictory goals of the two sub-tasks, i.e., person detection focuses on finding the commonness of all persons while person re-ID handles the differences among multiple identities. Therefore, it is crucial to reconcile the relationship between the two sub-tasks in a joint person search model. To this end, We present a novel approach called Norm-Aware Embedding to disentangle the person embedding into norm and angle for detection and re-ID respectively, allowing for both effective and efficient multi-task training. We further extend the proposal-level person embedding to pixel-level, whose discrimination ability is less affected by mis-alignment. We outperform other one-step methods by a large margin and achieve comparable performance to two-step methods on both CUHK-SYSU and PRW. Also, Our method is easy to train and resource-friendly, running at 12 fps on a single GPU.

关键词： Feature extraction Task analysis Training Detectors Standards Proposals Search problems

来源：评论

学校读者我要写书评

暂无评论

Clothed Human Performance Capture with a Double-layer Neural Radiance Fields

Clothed Human Performance Capture with a Double-layer Neural...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Kangkan Wang Guofeng Zhang Suxu Cong Jian Yang Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of CAD&CG Zhejiang University China

This paper addresses the challenge of capturing performance for the clothed humans from sparse-view or monocular videos. Previous methods capture the performance of full humans with a personalized template or recover the garments from a single frame with static human poses. However, it is inconvenient to extract cloth semantics and capture clothing motion with one-piece template, while single frame-based methods may suffer from instable tracking across videos. To address these problems, we propose a novel method for human performance capture by tracking clothing and human body motion separately with a double-layer neural radiance fields (NeRFs). Specifically, we propose a double-layer NeRFsfor the body and garments, and track the densely deforming template of the clothing and body by jointly optimizing the deformation fields and the canonical double-layer NeRFs. In the optimization, we introduce a physics-aware cloth simulation network which can help generate physically plausible cloth dynamics and body-cloth interactions. Compared with existing methods, our method is fully differentiable and can capture both the body and clothing motion robustly from dynamic videos. Also, our method represents the clothing with an independent NeRFs, allowing us to model implicit fields of general clothes feasibly. The experimental evaluations validate its effectiveness on real multi-view or monocular videos.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-class label Noise Learning via Loss Decomposition and Centroid Estimation

arXiv

引用

arXiv 2022年

作者： Ding, Yongliang Zhou, Tao Zhang, Chuang Luo, Yijing Tang, Juan Gong, Chen PCA Lab The Key Laboratory of Intelligent Perceptron and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Cyber Engineering Guangzhou University China

In real-world scenarios, many large-scale datasets often contain inaccurate labels, i.e., noisy labels, which may confuse model training and lead to performance degradation. To overcome this issue, label Noise Learning (LNL) has recently attracted much attention, and various methods have been proposed to design an unbiased risk estimator to the noise-free dataset to combat such label noise. Among them, a trend of works based on Loss Decomposition and Centroid Estimation (LDCE) has shown very promising performance. However, existing LNL methods based on LDCE are only designed for binary classification, and they are not directly extendable to multi-class situations. In this paper, we propose a novel multi-class robust learning method for LDCE, which is termed "MC-LDCE". Specifically, we decompose the commonly adopted loss (e.g., mean squared loss) function into a label-dependent part and a label-independent part, in which only the former is influenced by label noise. Further, by defining a new form of data centroid, we transform the recovery problem of a label-dependent part to a centroid estimation problem. Finally, by critically examining the mathematical expectation of clean data centroid given the observed noisy set, the centroid can be estimated which helps to build an unbiased risk estimator for multi-class learning. The proposed MC-LDCE method is general and applicable to different types (i.e., linear and nonlinear) of classification models. The experimental results on five public datasets demonstrate the superiority of the proposed MC-LDCE against other representative LNL methods in tackling multi-class label noise problem. © 2022, CC BY-NC-SA.

关键词： Learning systems

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：