Related papers: Semi-Supervised Co-Analysis of 3D Shape Styles fro…

Most of the existing self-supervised feature learning methods for 3D data either learn 3D features from point cloud data or from multi-view images. By exploring the inherent multi-modality attributes of 3D objects, in this paper, we propose…

Unsupervised point cloud completion aims at estimating the corresponding complete point cloud of a partial point cloud in an unpaired manner. It is a crucial but challenging problem since there is no paired partial-complete supervision that…

Deep-learning methods have recently started being employed for addressing surface-defect detection problems in industrial quality control. However, with a large amount of data needed for learning, often requiring high-precision labels, many…

Constrained image splicing detection and localization (CISDL) is a fundamental task of multimedia forensics, which detects splicing operation between two suspected images and localizes the spliced region on both images. Recent works regard…

In this paper, we focus on the two tasks of 3D shape abstraction and semantic analysis. This is in contrast to current methods, which focus solely on either 3D shape abstraction or semantic analysis. In addition, previous methods have had…

Unsupervised learning of global features for 3D shape analysis is an important research challenge because it avoids manual effort for supervised information collection. In this paper, we propose a view-based deep learning model called…

Labeled data used for training activity recognition classifiers are usually limited in terms of size and diversity. Thus, the learned model may not generalize well when used in real-world use cases. Semi-supervised learning augments labeled…

Recent advances in semi-supervised learning methods rely on estimating the categories of unlabeled data using a model trained on the labeled data (pseudo-labeling) and using the unlabeled data for various consistency-based regularization.…

Many existing approaches for 3D point cloud semantic segmentation are fully supervised. These fully supervised approaches heavily rely on large amounts of labeled training data that are difficult to obtain and cannot segment new classes…

Federated learning enables multiple clients, such as mobile phones and organizations, to collaboratively learn a shared model for prediction while protecting local data privacy. However, most recent research and applications of federated…

Recently, deep learning has experienced rapid expansion, contributing significantly to the progress of supervised learning methodologies. However, acquiring labeled data in real-world settings can be costly, labor-intensive, and sometimes…

To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…

Fine-grained 3D shape classification is important for shape understanding and analysis, which poses a challenging research problem. However, the studies on the fine-grained 3D shape classification have rarely been explored, due to the lack…

Face sketch synthesis has made great progress in the past few years. Recent methods based on deep neural networks are able to generate high quality sketches from face photos. However, due to the lack of training data (photo-sketch pairs),…

A significant issue in training deep neural networks to solve supervised learning tasks is the need for large numbers of labelled datapoints. The goal of semi-supervised learning is to leverage ubiquitous unlabelled data, together with…

Although semi-dense Simultaneous Localization and Mapping (SLAM) has been becoming more popular over the last few years, there is a lack of efficient methods for representing and processing their large scale point clouds. In this paper, we…

Existing state-of-the-art 3D point cloud understanding methods merely perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework that simultaneously solves the downstream high-level…

Contrastive Learning (CL) is a recent representation learning approach, which encourages inter-class separability and intra-class compactness in learned image representations. Since medical images often contain multiple semantic classes in…

Representing complex 3D objects as simple geometric primitives, known as shape abstraction, is important for geometric modeling, structural analysis, and shape synthesis. In this paper, we propose an unsupervised shape abstraction method to…

Pathology image segmentation across multiple centers encounters significant challenges due to diverse sources of heterogeneity including imaging modalities, organs, and scanning equipment, whose variability brings representation bias and…