作者:
Wan, ShengPan, ShiruiZhong, PingChang, XiaojunYang, JianGong, ChenPca Laboratory
Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China
Faculty of Information Technology Monash University ClaytonVIC3800 Australia National Key Laboratory of Science and Technology on Atr
National University of Defense Technology Changsha410073 China Pca Laboratory
Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing210094 China Department of Computing
Hong Kong Polytechnic University Hong Kong Hong Kong
Recently, graph convolutional network (GCN) has progressed significantly and gained increasing attention in hyperspectral image (HSI) classification due to its impressive representation power. However, existing GCN-ba...
详细信息
作者:
Chen GongHong ShiTongliang LiuChuang ZhangJian YangDacheng TaoPCA Lab
the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing P.R. China PCA Lab
the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security the School of Computer Science and Engineering
Nanjing University of Science and Technology Nanjing P.R. China UBTECH Sydney Artificial Intelligence Centre
School of Computer Science Faculty of Engineering University of Sydney Darlington NSW Australia
This paper studies Positive and Unlabeled learning (PU learning), of which the target is to build a binary classifier where only positive data and unlabeled data are available for classifier training. To deal with the...
详细信息
This paper studies Positive and Unlabeled learning (PU learning), of which the target is to build a binary classifier where only positive data and unlabeled data are available for classifier training. To deal with the absence of negative training data, we first regard all unlabeled data as negative examples with false negative labels, and then convert PU learning into the risk minimization problem in the presence of such one-side label noise. Specifically, we propose a novel PU learning algorithm dubbed "Loss Decomposition and Centroid Estimation" (LDCE). By decomposing the loss function of corrupted negative examples into two parts, we show that only the second part is affected by the noisy labels. Thereby, we may estimate the centroid of corrupted negative set via an unbiased way to reduce the adverse impact of such label noise. Furthermore, we propose the "Kernelized LDCE" (KLDCE) by introducing the kernel trick, and show that KLDCE can be easily solved by combining Alternative Convex Search (ACS) and Sequential Minimal Optimization (SMO). Theoretically, we derive the generalization error bound which suggests that the generalization risk of our model converges to the empirical risk with the order of O(1/√k+1/√{n-k}+1/√n) ( n and k are the amounts of training data and positive data correspondingly). Experimentally, we conduct intensive experiments on synthetic dataset, UCI benchmark datasets and real-world datasets, and the results demonstrate that our approaches (LDCE and KLDCE) achieve the top-level performance when compared with both classic and state-of-the-art PU learning methods.
作者:
Zou, HongliangYang, JianPCA 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 210094 China
Background and objective: Functional connectivity (FC) based on resting-state functional magnetic resonance imaging (rs-fMRI) is an effective approach to describe the neural interaction between distributed brain regio...
详细信息
In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. Most successful 3D detectors take the projection constraint from the 3D bounding box to the 2D box as an important co...
详细信息
作者:
Han, ZongyanFu, ZhenyongYang, JianPCA 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
Zero-shot object recognition or zero-shot learning aims to transfer the object recognition ability among the semantically related categories, such as fine-grained animal or bird species. However, the images of differe...
详细信息
In this paper, we propose an effective point cloud generation method, which can generate multi-resolution point clouds of the same shape from a latent vector. Specifically, we develop a novel progressive deconvolution...
详细信息
This work addresses the problem of 3D human pose and shape estimation from a sequence of point clouds. Existing sequential 3D human shape estimation methods mainly focus on the template model fitting from a sequence o...
详细信息
ISBN:
(数字)9781728171685
ISBN:
(纸本)9781728171692
This work addresses the problem of 3D human pose and shape estimation from a sequence of point clouds. Existing sequential 3D human shape estimation methods mainly focus on the template model fitting from a sequence of depth images or the parametric model regression from a sequence of RGB images. In this paper, we propose a novel sequential 3D human pose and shape estimation framework from a sequence of point clouds. Specifically, the proposed framework can regress 3D coordinates of mesh vertices at different resolutions from the latent features of point clouds. Based on the estimated 3D coordinates and features at the low resolution, we develop a spatial-temporal mesh attention convolution (MAC) to predict the 3D coordinates of mesh vertices at the high resolution. By assigning specific attentional weights to different neighboring points in the spatial and temporal domains, our spatial-temporal MAC can capture structured spatial and temporal features of point clouds. We further generalize our framework to the real data of human bodies with a weakly supervised fine-tuning method. The experimental results on SURREAL, Human3.6M, DFAUST and the real detailed data demonstrate that the proposed approach can accurately recover the 3D body model sequence from a sequence of point clouds.
作者:
Wang, YunZhang, TongCui, ZhenXu, ChunyanYang, JianPCA 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
Graph convolutional neural network (GCN) has effectively boosted the multi-label image recognition task by introducing label dependencies based on statistical label co-occurrence of data. However, in previous methods,...
详细信息
作者:
Mingmei ChengLe HuiJin XieJian YangHui KongPCA 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
In this paper, we propose a cascaded non-local neural network for point cloud segmentation. The proposed network aims to build the long-range dependencies of point clouds for the accurate segmentation. Specifically, w...
详细信息
ISBN:
(数字)9781728162126
ISBN:
(纸本)9781728162133
In this paper, we propose a cascaded non-local neural network for point cloud segmentation. The proposed network aims to build the long-range dependencies of point clouds for the accurate segmentation. Specifically, we develop a novel cascaded non-local module, which consists of the neighborhood-level, superpoint-level and global-level non-local blocks. First, in the neighborhood-level block, we extract the local features of the centroid points of point clouds by assigning different weights to the neighboring points. The extracted local features of the centroid points are then used to encode the superpoint-level block with the non-local operation. Finally, the global-level block aggregates the non-local features of the superpoints for semantic segmentation in an encoder-decoder framework. Benefiting from the cascaded structure, geometric structure information of different neighborhoods with the same label can be propagated. In addition, the cascaded structure can largely reduce the computational cost of the original non-local operation on point clouds. Experiments on different indoor and outdoor datasets show that our method achieves state-of-the-art performance and effectively reduces the time consumption and memory occupation.
作者:
Jie XuLin ZhaoShanshan ZhangChen GongJian YangPCA 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 210094 China State Key Laboratory of Integrated Services Networks
Xidian Univeristy Xi’an 710071 China
Object keypoints detection and classification are both central research topics in computervision . Due to their wide range potential applications in the real world, substantial efforts have been taken to advance thei...
Object keypoints detection and classification are both central research topics in computervision . Due to their wide range potential applications in the real world, substantial efforts have been taken to advance their performance. However, these two related tasks are mainly treated separately in previous works. We argue that keypoints detection and classification can be complementary tasks and beneficial to each other. Knowing the category of a object is able to reduce the searching space of keypoints detection models and facilitate more precise localization . On the other hand, having the knowledge of object keypoints can make classification models pay more attention on areas that are more associated with the object, which will inevitably promote classification accuracy . Embracing this observation, we propose to model keypoints detection and classification in a multi-task learning framework. Specifically, a multi-task deep network is designed and trained to conduct both tasks, where we devise the model structure delicately to carry out sufficient training of both tasks. Extensive experiments are set up on the AIFASHION DATASET and Human3.6M DATASET to validate our proposal, we show that our algorithm outperforms separate models trained individually on each task.
暂无评论