Related papers: Differentiated Information Mining: A Semi-supervis…
Imperfect labels are ubiquitous in real-world datasets and seriously harm the model performance. Several recent effective methods for handling noisy labels have two key steps: 1) dividing samples into cleanly labeled and wrongly labeled…
We consider a family of problems that are concerned about making predictions for the majority of unlabeled, graph-structured data samples based on a small proportion of labeled samples. Relational information among the data samples, often…
Semi-supervised learning (SSL) is a class of supervised learning tasks and techniques that also exploits the unlabeled data for training. SSL significantly reduces labeling related costs and is able to handle large data sets. The primary…
We propose a novel semi-supervised learning (SSL) method that adopts selective training with pseudo labels. In our method, we generate hard pseudo-labels and also estimate their confidence, which represents how likely each pseudo-label is…
Given a small set of labeled data and a large set of unlabeled data, semi-supervised learning (SSL) attempts to leverage the location of the unlabeled datapoints in order to create a better classifier than could be obtained from supervised…
Deep neural networks have been widely used in communication signal recognition and achieved remarkable performance, but this superiority typically depends on using massive examples for supervised learning, whereas training a deep neural…
Semi-supervised learning frameworks usually adopt mutual learning approaches with multiple submodels to learn from different perspectives. To avoid transferring erroneous pseudo labels between these submodels, a high threshold is usually…
Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.…
Graph-based semi-supervised node classification (GraphSSC) has wide applications, ranging from networking and security to data mining and machine learning, etc. However, existing centralized GraphSSC methods are impractical to solve many…
Image recognition is an important topic in computer vision and image processing, and has been mainly addressed by supervised deep learning methods, which need a large set of labeled images to achieve promising performance. However, in most…
Semi-supervised multi-label learning (SSMLL) aims to address the challenge of limited labeled data in multi-label learning (MLL) by leveraging unlabeled data to improve the model's performance. While pseudo-labeling has become a dominant…
We evaluate the effectiveness of semi-supervised learning (SSL) on a realistic benchmark where data exhibits considerable class imbalance and contains images from novel classes. Our benchmark consists of two fine-grained classification…
Deep learning is pushing the state-of-the-art in many computer vision applications. However, it relies on large annotated data repositories, and capturing the unconstrained nature of the real-world data is yet to be solved. Semi-supervised…
The premise of semi-supervised learning (SSL) is that combining labeled and unlabeled data yields significantly more accurate models. Despite empirical successes, the theoretical understanding of SSL is still far from complete. In this…
Recent state-of-the-art methods in semi-supervised learning (SSL) combine consistency regularization with confidence-based pseudo-labeling. To obtain high-quality pseudo-labels, a high confidence threshold is typically adopted. However, it…
Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods…
Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph…
The paper introduces Diff-Filter, a multichannel speech enhancement approach based on the diffusion probabilistic model, for improving speaker verification performance under noisy and reverberant conditions. It also presents a new two-step…
Designing learning-based no-reference (NR) video quality assessment (VQA) algorithms for camera-captured videos is cumbersome due to the requirement of a large number of human annotations of quality. In this work, we propose a…
Graph-based methods have been demonstrated as one of the most effective approaches for semi-supervised learning, as they can exploit the connectivity patterns between labeled and unlabeled data samples to improve learning performance.…