Class-aware contrastive semi-supervised learning
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw
data utilization. However, its training procedure suffers from confirmation bias due to the …
data utilization. However, its training procedure suffers from confirmation bias due to the …
Debiased self-training for semi-supervised learning
Deep neural networks achieve remarkable performances on a wide range of tasks with the
aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor …
aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor …
Daso: Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning
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 …
world application due to severely biased pseudo-labels caused by (1) class imbalance and …
Safe-student for safe deep semi-supervised learning with unseen-class unlabeled data
Deep semi-supervised learning (SSL) methods aim to take advantage of abundant
unlabeled data to improve the algorithm performance. In this paper, we consider the …
unlabeled data to improve the algorithm performance. In this paper, we consider the …
Open-sampling: Exploring out-of-distribution data for re-balancing long-tailed datasets
Deep neural networks usually perform poorly when the training dataset suffers from extreme
class imbalance. Recent studies found that directly training with out-of-distribution data (ie …
class imbalance. Recent studies found that directly training with out-of-distribution data (ie …
Rethinking pseudo-labeling for semi-supervised facial expression recognition with contrastive self-supervised learning
B Fang, X Li, G Han, J He - IEEE Access, 2023 - ieeexplore.ieee.org
Self-supervised learning for semi-supervised facial expression recognition aims to avoid the
need to collect expensive labeled facial expression data. Existing methods demonstrate an …
need to collect expensive labeled facial expression data. Existing methods demonstrate an …
Systematic comparison of semi-supervised and self-supervised learning for medical image classification
In typical medical image classification problems labeled data is scarce while unlabeled data
is more available. Semi-supervised learning and self-supervised learning are two different …
is more available. Semi-supervised learning and self-supervised learning are two different …
Prompting scientific names for zero-shot species recognition
Trained on web-scale image-text pairs, Vision-Language Models (VLMs) such as CLIP can
recognize images of common objects in a zero-shot fashion. However, it is underexplored …
recognize images of common objects in a zero-shot fashion. However, it is underexplored …
Coreset sampling from open-set for fine-grained self-supervised learning
Deep learning in general domains has constantly been extended to domain-specific tasks
requiring the recognition of fine-grained characteristics. However, real-world applications for …
requiring the recognition of fine-grained characteristics. However, real-world applications for …
Rda: Reciprocal distribution alignment for robust semi-supervised learning
In this work, we propose Reciprocal Distribution Alignment (RDA) to address semi-
supervised learning (SSL), which is a hyperparameter-free framework that is independent of …
supervised learning (SSL), which is a hyperparameter-free framework that is independent of …