Related papers: MultiMatch: Multihead Consistency Regularization M…

Pseudo-labeling has proven to be a promising semi-supervised learning (SSL) paradigm. Existing pseudo-labeling methods commonly assume that the class distributions of training data are balanced. However, such an assumption is far from…

In this work, we propose MixMOOD - a systematic approach to mitigate effect of class distribution mismatch in semi-supervised deep learning (SSDL) with MixMatch. This work is divided into two components: (i) an extensive out of distribution…

Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks. Currently, there are two popular approaches to make use of…

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,…

The scarcity of labeled data in real-world scenarios is a critical bottleneck of deep learning's effectiveness. Semi-supervised semantic segmentation has been a typical solution to achieve a desirable tradeoff between annotation cost and…

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…

Adapting vision-language models (VLMs) to downstream tasks with pseudolabels has gained increasing attention. A major obstacle is that the pseudolabels generated by VLMs tend to be imbalanced, leading to inferior performance. While existing…

Federated Semi-Supervised Learning (FSSL) aims to leverage unlabeled data across clients with limited labeled data to train a global model with strong generalization ability. Most FSSL methods rely on consistency regularization with…

Semi-supervised learning (SSL) is one of the dominant approaches to address the annotation bottleneck of supervised learning. Recent SSL methods can effectively leverage a large repository of unlabeled data to improve performance while…

Supervised machine learning (ML) algorithms are aimed at maximizing classification performance under available energy and storage constraints. They try to map the training data to the corresponding labels while ensuring generalizability to…

Despite the remarkable performance of supervised medical image segmentation models, relying on a large amount of labeled data is impractical in real-world situations. Semi-supervised learning approaches aim to alleviate this challenge using…

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…

Semi-supervised semantic segmentation (SSS) aims at learning rich visual knowledge from cheap unlabeled images to enhance semantic segmentation capability. Among recent works, UniMatch improves its precedents tremendously by amplifying the…

In this paper, we study semi-supervised Handwritten Mathematical Expression Recognition (HMER) via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization framework, termed SemiHMER, which…

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…

Semi-supervised learning (SSL) leverages abundant unlabeled data alongside limited labeled data to enhance learning. As vision foundation models (VFMs) increasingly serve as the backbone of vision applications, it remains unclear how SSL…

Recent state-of-the-art methods in imbalanced semi-supervised learning (SSL) rely on confidence-based pseudo-labeling with consistency regularization. To obtain high-quality pseudo-labels, a high confidence threshold is typically adopted.…

Semi-Supervised Learning (SSL) has shown its strong ability in utilizing unlabeled data when labeled data is scarce. However, most SSL algorithms work under the assumption that the class distributions are balanced in both training and test…

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…

Person re-identification (re-ID) aims at identifying the same persons' images across different cameras. However, domain diversities between different datasets pose an evident challenge for adapting the re-ID model trained on one dataset to…