检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Wei, Xiu-Shen Xu, Yu-Yan Yao, Yazhou Wei, Jia Xi, Si Xu, Wenyuan Zhang, Weidong Lv, Xiaoxin Fu, Dengpan Li, Qing Chen, Baoying Guo, Haojie Xue, Taolue Jing, Haipeng Wang, Zhiheng Zhang, Tianming Zhang, Mingwen 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 China Jiangsu Key Lab of Image Video Understanding for Social Security China Netease Games AI Lab Netease Yidun AI Lab

WebFG 2020 is an international challenge hosted by Nanjing University of Science and Technology, University of Edinburgh, Nanjing University, The University of Adelaide, Waseda University, etc. This challenge mainly pays attention to the webly-supervised fine-grained recognition problem. In the literature, existing deep learning methods highly rely on large-scale and high-quality labeled training data, which poses a limitation to their practicability and scalability in real world applications. In particular, for fine-grained recognition, a visual task that requires professional knowledge for labeling, the cost of acquiring labeled training data is quite high. It causes extreme difficulties to obtain a large amount of high-quality training data. Therefore, utilizing free web data to train fine-grained recognition models has attracted increasing attentions from researchers in the fine-grained community. This challenge expects participants to develop webly-supervised fine-grained recognition methods, which leverages web images in training fine-grained recognition models to ease the extreme dependence of deep learning methods on large-scale manually labeled datasets and to enhance their practicability and scalability. In this technical report, we have pulled together the top WebFG 2020 solutions of total 54 competing teams, and discuss what methods worked best across the set of winning teams, and what surprisingly did not help. © 2020, CC BY.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Two-View Fusion based Convolutional Neural Network for Urban Road Detection

Two-View Fusion based Convolutional Neural Network for Urban...

引用

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Shuo Gu Yigong Zhang Jian Yang Jose M. Alvarez Hui Kong PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and 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 NVIDIA Santa Clara CA USA

In this paper, we propose a two-view fusion based convolutional neural network to estimate road areas in urban environments with LiDAR point clouds as input only. The proposed network takes two transformed LiDAR data representations, the LiDAR imageries and the camera-perspective maps, as inputs. It outputs pixel-wise road detection results in both the LiDAR's imagery view and the camera's perspective view simultaneously, in an end-to-end manner. To make better use of the data associations between two representations, we construct a novel mapping layer to transform features from the LiDAR's imagery view to the camera's perspective view in order to strengthen the road detection performance in the camera's perspective view. Experiments on the KITTI-Road dataset show that the proposed network can achieve the state-of-the-art performance among all LiDAR-only methods in real time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust unsupervised feature selection by nonnegative sparse subspace learning

引用

Neurocomputing 2019年 334卷 156-171页

作者： Wei Zheng Hui Yan Jian Yang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing PR China School of Computer Engineering Jinling Institute of Technology Nanjing PR China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Key Laboratory of Trusted Cloud Computing and Big Data Analysis Nanjing Xiaozhuang University Nanjing PR China

Sparse subspace learning has been demonstrated to be effective in data mining and machine learning. In this paper, we cast the unsupervised feature selection scenario as a matrix factorization problem from the viewpoint of sparse subspace learning. By minimizing the reconstruction residual, the learned feature weight matrix with the l 2,1 -norm and the non-negative constraints not only removes the irrelevant features, but also captures the underlying low dimensional structure of the data points. Meanwhile in order to enhance the model's robustness, l 1 -norm error function is used to resistant to outliers and sparse noise. An efficient iterative algorithm is introduced to optimize this non-convex and non-smooth objective function and the proof of its convergence is given. Although, there is a subtraction item in our multiplicative update rule, we validate its non-negativity. The superiority of our model is demonstrated by comparative experiments on various original datasets with and without malicious pollution.

关键词： Subspace learning Non-negative matrix factorization Unsupervised feature selection

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised 3D Scene Flow Estimation Guided by Superpoints

Self-Supervised 3D Scene Flow Estimation Guided by Superpoin...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Yaqi Shen Le Hui Jin Xie Jian Yang PCA Lab Nanjing University of Science and Technology Nanjing China 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

3D scene flow estimation aims to estimate point-wise motions between two consecutive frames of point clouds. Superpoints, i.e., points with similar geometric features, are usually employed to capture similar motions of local regions in 3D scenes for scene flow estimation. However, in existing methods, superpoints are generated with the offline clustering methods, which cannot characterize local regions with similar motions for complex 3D scenes well, leading to inaccurate scene flow estimation. To this end, we propose an iterative end-to-end super point based scene flow estimation framework, where the superpoints can be dynamically updated to guide the point-level flow prediction. Specifically, our framework consists of a flow guided superpoint generation module and a superpoint guided flow refinement module. In our superpoint generation module, we utilize the bidirectional flow information at the previous iteration to obtain the matching points of points and superpoint centers for soft point-to-superpoint association construction, in which the superpoints are generated for pairwise point clouds. With the generated superpoints, we first reconstruct the flow for each point by adaptively aggregating the superpoint-level flow, and then encode the consistency between the reconstructed flow of pairwise point clouds. Finally, we feed the consistency encoding along with the reconstructed flow into GRU to refine point-level flow. Extensive experiments on several different datasets show that our method can achieve promising performance. Code is available at https://***/supersyq/SPFlowNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection With Sky-Annotated Dataset

arXiv

引用

arXiv 2024年

作者： Xiao, Mengxuan Dai, Qun Zhu, Yiming Guo, Kehua Wang, Huan Shu, Xiangbo Yang, Jian Dai, Yimian School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China PCALab 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 China School of Computer Science and Engineering Central South University China

Infrared small target detection poses unique challenges due to the scarcity of intrinsic target features and the abundance of similar background distractors. We argue that background semantics play a pivotal role in distinguishing visually similar objects for this task. To address this, we introduce a new task-clustered infrared small target detection, and present DenseSIRST, a novel benchmark dataset that provides per-pixel semantic annotations for background regions, enabling the transition from sparse to dense target detection. Leveraging this dataset, we propose the Background-Aware Feature Exchange Network (BAFE-Net), which transforms the detection paradigm from a single task focused on the foreground to a multi-task architecture that jointly performs target detection and background semantic segmentation. BAFE-Net introduces a dynamic cross-task feature hard-exchange mechanism to embed target and background semantics between the two tasks. Furthermore, we propose the Background-Aware Gaussian Copy-Paste (BAG-CP) method, which selectively pastes small targets into sky regions during training, avoiding the creation of false alarm targets in complex non-sky backgrounds. Extensive experiments validate the effectiveness of BAG-CP and BAFE-Net in improving target detection accuracy while reducing false alarms. The DenseSIRST dataset, code, and trained models are available at https://***/GrokCV/BAFE-Net. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Grouped Adaptive Loss Weighting for Person Search

arXiv

引用

arXiv 2022年

作者： Tian, Yanling Chen, Di Liu, Yunan Zhang, Shanshan Yang, Jian School of Artificial Intelligence Dalian Maritime University China 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 China

Person search is an integrated task of multiple sub-tasks such as foreground/background classification, bounding box regression and person re-identification. Therefore, person search is a typical multi-task learning problem, especially when solved in an end-to-end manner. Recently, some works enhance person search features by exploiting various auxiliary information, e.g. person joint key-points, body part position, attributes, etc., which brings in more tasks and further complexifies a person search model. The inconsistent convergence rate of each task could potentially harm the model optimization. A straightforward solution is to manually assign different weights to different tasks, compensating for the diverse convergence rates. However, given the special case of person search, i.e. with a large number of tasks, it is impractical to weight the tasks manually. To this end, we propose a Grouped Adaptive Loss Weighting (GALW) method which adjusts the weight of each task automatically and dynamically. Specifically, we group tasks according to their convergence rates. Tasks within the same group share the same learnable weight, which is dynamically assigned by considering the loss uncertainty. Experimental results on two typical benchmarks, CUHK-SYSU and PRW, demonstrate the effectiveness of our method. © 2022, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation

arXiv

引用

arXiv 2023年

作者： An, Xiaoqi Zhao, Lin Gong, Chen Wang, Nannan Wang, Di 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 State Key Laboratory of Integrated Services Networks Xidian University China

High-resolution representation is essential for achieving good performance in human pose estimation models. To obtain such features, existing works utilize high-resolution input images or fine-grained image tokens. However, this dense high-resolution representation brings a significant computational burden. In this paper, we address the following question: "Only sparse human keypoint locations are detected for human pose estimation, is it really necessary to describe the whole image in a dense, high-resolution manner?" Based on dynamic transformer models, we propose a framework that only uses Sparse High-resolution Representations for human Pose estimation (SHaRPose). In detail, SHaRPose consists of two stages. At the coarse stage, the relations between image regions and keypoints are dynamically mined while a coarse estimation is generated. Then, a quality predictor is applied to decide whether the coarse estimation results should be refined. At the fine stage, SHaRPose builds sparse high-resolution representations only on the regions related to the keypoints and provides refined high-precision human pose estimations. Extensive experiments demonstrate the outstanding performance of the proposed method. Specifically, compared to the state-of-the-art method ViTPose, our model SHaRPose-Base achieves 77.4 AP (+0.5 AP) on the COCO validation set and 76.7 AP (+0.5 AP) on the COCO test-dev set, and infers at a speed of 1.4× faster than ViTPose-Base. Code is available at https://***/AnxQ/sharpose. Copyright © 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

A general elimination strategy for camera motion estimation

A general elimination strategy for camera motion estimation

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Yaqing Ding Yingna Su Chengzhong Xu Jian Yang Hui Kong Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Faculty of Science and Technology University of Macau Macau SAR China

Camera motion estimation, such as relative pose estimation and absolute pose estimation, are fundamental problems in computer vision and robotics. To obtain the motion parameters, classical methods rely on studying the properties of the geometric matrices, e.g., rotation matrix, essential matrix, homography matrix. The well known five-point algorithm was successfully derived using the singular constraint and trace constraints on the essential matrix. However, finding all the algebraic constraints is not always trivial for some recent problems. In this paper, we propose a simple and general technique to find complete algebraic constraints so that we can derive efficient algorithms. We show that using the quaternion to formulate the rotation matrix we can eliminate any unknowns from the original equations and obtain constraints on the rest of the unknowns based on Gröbner basis. We demonstrate that this approach can be applied to almost all the camera motion estimation and show its improvement compared to the existing methods. Further more, based on this elimination technique, we exploit new constraints for the relative pose estimation with gravity prior, and derive a new globally optimal algorithm to this problem. We compare our algorithm with the state-of-the-art methods on both synthetic and real-world data, and show the benefits including accuracy and efficiency.

关键词： computer vision Automation Motion estimation Quaternions Conferences Pose estimation Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

Improved multi-scale dynamic feature encoding network for image demoiréing

引用

Pattern Recognition 2021年 116卷 107970-107970页

作者： Cheng, Xi Fu, Zhenyong Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and 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

The popularity of smartphones with digital cameras makes photographing using smartphones an important daily activity. Moiré patterns can easily appear when shooting objects with rich textures, such as computer screens, and will severely degrade the image quality. image demoiréing is an important image restoration task that aims to remove moiré patterns and reveal the underlying clean image. Two key properties of moiré patterns—the widely distributed frequency spectrum and the dynamic nature of moiré textures—challenge the image demoiréing task. In this paper, we propose an improved Multi-scale convolutional network with Dynamic feature encoding for image DeMoiréing (MDDM+). We design two schemes in our network to respectively attack the broad frequency spectrum and the dynamic texture of moiré: a multi-scale structure to process images at different spatial resolutions and a dynamic feature encoding module to encode the texture dynamically. To capture more moiré and texture information from different frequencies, we further propose a novel L₁ wavelet loss used to train our model. Extensive experiments on two benchmarks show that our proposed image demoiréing network can outperform the state of the arts in terms of fidelity as well as perception. © 2021

关键词： Dynamic feature encoding image demoiréing Moiré pattern Screen shot images

来源：评论

学校读者我要写书评

暂无评论

Watermarking for out-of-distribution detection 22

Watermarking for out-of-distribution detection

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Qizhou Wang Feng Liu Yonggang Zhang Jing Zhang Chen Gong Tongliang Liu Bo Han Department of Computer Science Hong Kong Baptist University School of Mathematics and Statistics The University of Melbourne School of Computer Science The University of Sydney PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of MoE and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology TML Lab The University of Sydney

ISBN: (纸本)9781713871088

Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models. However, existing methods largely ignore the reprogramming property of deep models and thus may not fully unleash their intrinsic strength: without modifying parameters of a well-trained deep model, we can reprogram this model for a new purpose via data-level manipulation (e.g., adding a specific feature perturbation to the data). This property motivates us to reprogram a classification model to excel at OOD detection (a new task), and thus we propose a general methodology named watermarking in this paper. Specifically, we learn a unified pattern that is superimposed onto features of original data, and the model's detection capability is largely boosted after watermarking. Extensive experiments verify the effectiveness of watermarking, demonstrating the significance of the reprogramming property of deep models in OOD detection.

关键词：

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：