Related papers: CAST: Cluster-Aware Self-Training for Tabular Data…
Self-training has become a popular semi-supervised learning technique for leveraging unlabeled data. However, the over-confidence of pseudo-labels remains a key challenge. In this paper, we propose a novel \emph{graph-based…
Recently, temporal action localization (TAL) has garnered significant interest in information retrieval community. However, existing supervised/weakly supervised methods are heavily dependent on extensive labeled temporal boundaries and…
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…
Recent studies have shown that pseudo labels can contribute to unsupervised domain adaptation (UDA) for speaker verification. Inspired by the self-training strategies that use an existing classifier to label the unlabeled data for…
Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection…
Neural sequence labeling (NSL) aims at assigning labels for input language tokens, which covers a broad range of applications, such as named entity recognition (NER) and slot filling, etc. However, the satisfying results achieved by…
The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched. In this paper, we show that self-training (ST) combined with an uncertainty-based…
Self-training is a classical approach in semi-supervised learning which is successfully applied to a variety of machine learning problems. Self-training algorithm generates pseudo-labels for the unlabeled examples and progressively refines…
Deep Learning heavily depends on large labeled datasets which limits further improvements. While unlabeled data is available in large amounts, in particular in image recognition, it does not fulfill the closed world assumption of…
Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this…
Answer selection in open-domain dialogues aims to select an accurate answer from candidates. Recent success of answer selection models hinges on training with large amounts of labeled data. However, collecting large-scale labeled data is…
Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confidence issue brought by the hard labels, even some…
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…
Unlike traditional supervised learning, in many settings only partial feedback is available. We may only observe outcomes for the chosen actions, but not the counterfactual outcomes associated with other alternatives. Such settings…
Semi-supervised learning on class-imbalanced data, although a realistic problem, has been under studied. While existing semi-supervised learning (SSL) methods are known to perform poorly on minority classes, we find that they still generate…
Semi-supervised learning leverages unlabeled data to enhance model performance, addressing the limitations of fully supervised approaches. Among its strategies, pseudo-supervision has proven highly effective, typically relying on one or…
Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of…
Pseudo-label (PL) filtering forms a crucial part of Self-Training (ST) methods for unsupervised domain adaptation. Dropout-based Uncertainty-driven Self-Training (DUST) proceeds by first training a teacher model on source domain labeled…
Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets. However, it is prohibitively time-costly and labor-expensive to collect sufficient labeled data in most realistic…
Models capable of leveraging unlabelled data are crucial in overcoming large distribution gaps between the acquired datasets across different imaging devices and configurations. In this regard, self-training techniques based on…