Related papers: An Uncertainty-Aware Pseudo-Label Selection Framew…
Semi-supervised semantic segmentation aims to learn from a small amount of labeled data and plenty of unlabeled ones for the segmentation task. The most common approach is to generate pseudo-labels for unlabeled images to augment the…
Recent advances in semi-supervised learning have shown tremendous potential in overcoming a major barrier to the success of modern machine learning algorithms: access to vast amounts of human-labeled training data. Previous algorithms based…
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit. To reduce the requirement of labels, a semi-supervised meta-training (SSMT) setting has been proposed for FSL,…
In machine learning, one must acquire labels to help supervise a model that will be able to generalize to unseen data. However, the labeling process can be tedious, long, costly, and error-prone. It is often the case that most of our data…
Domain adaptive semantic segmentation aims to learn a model with the supervision of source domain data, and produce satisfactory dense predictions on unlabeled target domain. One popular solution to this challenging task is self-training,…
Positive and Unlabeled (PU) learning, a binary classification model trained with only positive and unlabeled data, generally suffers from overfitted risk estimation due to inconsistent data distributions. To address this, we introduce a…
The majority of existing Unsupervised Domain Adaptation (UDA) methods presumes source and target domain data to be simultaneously available during training. Such an assumption may not hold in practice, as source data is often inaccessible…
In this work, we propose a simple yet effective meta-learning algorithm in semi-supervised learning. We notice that most existing consistency-based approaches suffer from overfitting and limited model generalization ability, especially when…
With the progress of sensor technology in wearables, the collection and analysis of PPG signals are gaining more interest. Using Machine Learning, the cardiac rhythm corresponding to PPG signals can be used to predict different tasks such…
Semi-supervised learning (SSL) has recently proven to be an effective paradigm for leveraging a huge amount of unlabeled data while mitigating the reliance on large labeled data. Conventional methods focused on extracting a pseudo label…
In recent years, neural architecture-based recommender systems have achieved tremendous success, but they still fall short of expectation when dealing with highly sparse data. Self-supervised learning (SSL), as an emerging technique for…
This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…
Learning exists in the context of data, yet notions of confidence typically focus on model predictions, not label quality. Confident learning (CL) is an alternative approach which focuses instead on label quality by characterizing and…
We approach the challenge of addressing semi-supervised domain generalization (SSDG). Specifically, our aim is to obtain a model that learns domain-generalizable features by leveraging a limited subset of labelled data alongside a…
Regularization is an effective way to promote the generalization performance of machine learning models. In this paper, we focus on label smoothing, a form of output distribution regularization that prevents overfitting of a neural network…
Pseudo-labeling (PL) has been shown to be effective in semi-supervised automatic speech recognition (ASR), where a base model is self-trained with pseudo-labels generated from unlabeled data. While PL can be further improved by iteratively…
Training neural networks using limited annotations is an important problem in the medical domain. Deep Neural Networks (DNNs) typically require large, annotated datasets to achieve acceptable performance which, in the medical domain, are…
Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight…
Domain transfer is a prevalent challenge in modern neural Information Retrieval (IR). To overcome this problem, previous research has utilized domain-specific manual annotations and synthetic data produced by consistency filtering to…
Most recent semi-supervised deep learning (deep SSL) methods used a similar paradigm: use network predictions to update pseudo-labels and use pseudo-labels to update network parameters iteratively. However, they lack theoretical support and…