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.
This work reviews the results of the NTIRE 2023 Challenge on image Shadow Removal. The described set of solutions were proposed for a novel dataset, which captures a wide range of object-light interactions. It consist...
详细信息
Unsupervised learning technology has caught up with or even surpassed supervised learning technology in general object classification (GOC) and person re-identification (re-ID). However, it is found that the unsupervi...
详细信息
Graph classification is a fundamental but challenging issue for numerous real-world applications. Despite recent great progress in image/video classification, convolutional neural networks (CNNs) cannot yet cater to g...
详细信息
Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification. However, the current GCN-based methods treat graph cons...
详细信息
Contrastive learning (CL) pretrains feature embeddings to scatter instances in the feature space so that the training data can be well discriminated. Most existing CL techniques usually encourage learning such feature...
ISBN:
(纸本)9781713871088
Contrastive learning (CL) pretrains feature embeddings to scatter instances in the feature space so that the training data can be well discriminated. Most existing CL techniques usually encourage learning such feature embeddings in the high-dimensional space to maximize the instance discrimination. However, this practice may lead to undesired results where the scattering instances are sparsely distributed in the high-dimensional feature space, making it difficult to capture the underlying similarity between pairwise instances. To this end, we propose a novel framework called contrastive learning with low-dimensional reconstruction (CLLR), which adopts a regularized projection layer to reduce the dimensionality of the feature embedding. In CLLR, we build the sparse/low-rank regularizer to adaptively reconstruct a low-dimensional projection space while preserving the basic objective for instance discrimination, and thus successfully learning contrastive embeddings that alleviate the above issue. Theoretically, we prove a tighter error bound for CLLR; empirically, the superiority of CLLR is demonstrated across multiple domains. Both theoretical and experimental results emphasize the significance of learning low-dimensional contrastive embeddings.
Synthetic Aperture Radar (SAR) target detection has long been impeded by inherent speckle noise and the prevalence of diminutive, ambiguous targets. While deep neural networks have advanced SAR target detection, their...
详细信息
Convolutional Neural Network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only...
详细信息
With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers...
详细信息
Point Cloud Registration (PCR) is a critical and challenging task in computervision and robotics. One of the primary difficulties in PCR is identifying salient and meaningful points that exhibit consistent semantic a...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
Point Cloud Registration (PCR) is a critical and challenging task in computervision and robotics. One of the primary difficulties in PCR is identifying salient and meaningful points that exhibit consistent semantic and geometric properties across different scans. Previous methods have encountered challenges with ambiguous matching due to the similarity among patch blocks throughout the entire point cloud and the lack of consideration for efficient global geometric consistency. To address these issues, we propose a new framework that includes several novel techniques. Firstly, we introduce a semantic-aware geometric encoder that combines object-level and patch-level semantic information. This encoder significantly improves registration recall by reducing ambiguity in patch-level superpoint matching. Additionally, we incorporate a prior knowledge approach that utilizes an intrinsic shape signature to identify salient points. This enables us to extract the most salient super points and meaningful dense points in the scene. Secondly, we introduce an innovative transformer that encodes High-Order (HO) geometric features. These features are crucial for identifying salient points within initial overlap regions while considering global high-order geometric consistency. We introduce an anchor node selection strategy to optimize this high-order transformer further. By encoding inter-frame triangle or polyhedron consistency features based on these anchor nodes, we can effectively learn high-order geometric features of salient super points. These high-order features are then propagated to dense points and utilized by a Sinkhorn matching module to identify critical correspondences for successful registration. The experiments conducted on the 3DMatch/3DLoMatch and KITTI datasets demonstrate the effectiveness of our method.
暂无评论