The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem. First, we propose a general pseudo-labeling framework that class-adaptively blends the semantic pseudo-label from a similarity-based classifier to the linear one from the linear classifier, after making the observation that both types of pseudo-labels have complementary properties in terms of bias. We further introduce a novel semantic alignment loss to establish balanced feature representation to reduce the biased predictions from the ...
In semi-supervised learning (SSL), a common practice is to learn consistent information from unlabel...
Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increas...
In this paper, we propose a novel co-learning framework (CoSSL) with decoupled representation learni...
Semi-supervised learning (SSL) has shown great promise in leveraging unlabeled data to improve model...
Semi-supervised learning (SSL) has shown great promise in leveragingunlabeled data to improve model ...
In this paper, we propose a novel co-learning framework (CoSSL) withdecoupled representation learnin...
Producing labels for unlabeled data is error-prone, making semi-supervised learning (SSL) troublesom...
Semi-supervised learning is a critical tool in reducing machine learning's dependence on labeled dat...
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active res...
The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited ...
Traditional class imbalanced learning algorithms require training data to be labeled, whereas semi-s...
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization...
Semi-supervised object detection (SSOD) attracts extensive research interest due to its great signif...
Semi-supervised learning (SSL) has achieved great success in leveraging a large amount of unlabeled ...
Semi-supervised learning (SSL) aims to avoid the need for collecting prohibitively expensive labelle...
In semi-supervised learning (SSL), a common practice is to learn consistent information from unlabel...
Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increas...
In this paper, we propose a novel co-learning framework (CoSSL) with decoupled representation learni...
Semi-supervised learning (SSL) has shown great promise in leveraging unlabeled data to improve model...
Semi-supervised learning (SSL) has shown great promise in leveragingunlabeled data to improve model ...
In this paper, we propose a novel co-learning framework (CoSSL) withdecoupled representation learnin...
Producing labels for unlabeled data is error-prone, making semi-supervised learning (SSL) troublesom...
Semi-supervised learning is a critical tool in reducing machine learning's dependence on labeled dat...
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active res...
The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited ...
Traditional class imbalanced learning algorithms require training data to be labeled, whereas semi-s...
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization...
Semi-supervised object detection (SSOD) attracts extensive research interest due to its great signif...
Semi-supervised learning (SSL) has achieved great success in leveraging a large amount of unlabeled ...
Semi-supervised learning (SSL) aims to avoid the need for collecting prohibitively expensive labelle...
In semi-supervised learning (SSL), a common practice is to learn consistent information from unlabel...
Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increas...
In this paper, we propose a novel co-learning framework (CoSSL) with decoupled representation learni...