Related papers: Task-Adaptive Pseudo Labeling for Transductive Met…
The pioneering method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. However, it…
Pseudo-labeling is a popular semi-supervised learning technique to leverage unlabeled data when labeled samples are scarce. The generation and selection of pseudo-labels heavily rely on labeled data. Existing approaches implicitly assume…
Zero-shot learning has received increasing interest as a means to alleviate the often prohibitive expense of annotating training data for large scale recognition problems. These methods have achieved great success via learning intermediate…
Despite the recent advances in multi-task learning of dense prediction problems, most methods rely on expensive labelled datasets. In this paper, we present a label efficient approach and look at jointly learning of multiple dense…
Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong. Existing consistent approaches…
This paper proposes a novel pseudo-labeling method for medical image segmentation that can perform learning on ``individual images'' to select effective pseudo-labels. We introduce Positive and Unlabeled Learning (PU learning), which uses…
Semi-supervised learning provides a solution to reduce the dependency of machine learning on labeled data. As one of the efficient semi-supervised techniques, self-training (ST) has received increasing attention. Several advancements have…
Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus,…
The success of deep learning methods hinges on the availability of large training datasets annotated for the task of interest. In contrast to human intelligence, these methods lack versatility and struggle to learn and adapt quickly to new…
Traditional semi-supervised learning (SSL) assumes that the feature distributions of labeled and unlabeled data are consistent which rarely holds in realistic scenarios. In this paper, we propose a novel SSL setting, where unlabeled samples…
In conventional domain adaptation, a critical assumption is that there exists a fully labeled domain (source) that contains the same label space as another unlabeled or scarcely labeled domain (target). However, in the real world, there…
Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set. In this work, we study the problem of training an…
Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learning adopt a…
Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent…
Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided. In some settings, however, it is feasible to actively select which points to label; the potential gain from…
There has been increased interest in devising learning techniques that combine unlabeled data with labeled data ? i.e. semi-supervised learning. However, to the best of our knowledge, no study has been performed across various techniques…
Neural network-based anomaly detection methods have shown to achieve high performance. However, they require a large amount of training data for each task. We propose a neural network-based meta-learning method for supervised anomaly…
Self-training is an effective approach to semi-supervised learning. The key idea is to let the learner itself iteratively generate "pseudo-supervision" for unlabeled instances based on its current hypothesis. In combination with consistency…
One of the primary challenges in Semi-supervised Domain Adaptation (SSDA) is the skewed ratio between the number of labeled source and target samples, causing the model to be biased towards the source domain. Recent works in SSDA show that…
Image-based 3D detection is an indispensable component of the perception system for autonomous driving. However, it still suffers from the unsatisfying performance, one of the main reasons for which is the limited training data.…