Related papers: Iterative Label Improvement: Robust Training by Co…

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…

One recent research demonstrated successful application of the label alignment property for unsupervised domain adaptation in a linear regression settings. Instead of regularizing representation learning to be domain invariant, the research…

We propose a selective learning method using meta-learning and deep reinforcement learning for medical image interpretation in the setting of limited labeling resources. Our method, MedSelect, consists of a trainable deep learning selector…

The recent success of deep learning is mostly due to the availability of big datasets with clean annotations. However, gathering a cleanly annotated dataset is not always feasible due to practical challenges. As a result, label noise is a…

For classification tasks, deep neural networks are prone to overfitting in the presence of label noise. Although existing methods are able to alleviate this problem at low noise levels, they encounter significant performance reduction at…

Effective convolutional neural networks are trained on large sets of labeled data. However, creating large labeled datasets is a very costly and time-consuming task. Semi-supervised learning uses unlabeled data to train a model with higher…

The industry increasingly relies on deep learning (DL) technology for manufacturing inspections, which are challenging to automate with rule-based machine vision algorithms. DL-powered inspection systems derive defect patterns from labeled…

Label-efficient time series representation learning, which aims to learn effective representations with limited labeled data, is crucial for deploying deep learning models in real-world applications. To address the scarcity of labeled time…

The accuracy of deep neural networks is significantly influenced by the effectiveness of mini-batch construction during training. In single-label scenarios, such as binary and multi-class classification tasks, it has been demonstrated that…

By redefining the conventional notions of layers, we present an alternative view on finitely wide, fully trainable deep neural networks as stacked linear models in feature spaces, leading to a kernel machine interpretation. Based on this…

Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective…

Despite the recent advances in multi-task learning of dense prediction problems, most methods rely on expensive labelled datasets. In this paper, we present a label efficient approach and look at jointly learning of multiple dense…

We propose a semi-supervised text classifier based on self-training using one positive and one negative property of neural networks. One of the weaknesses of self-training is the semantic drift problem, where noisy pseudo-labels accumulate…

Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…

The deep neural networks used in modern computer vision systems require enormous image datasets to train them. These carefully-curated datasets typically have a million or more images, across a thousand or more distinct categories. The…

Deep neural networks have proven to be highly effective when large amounts of data with clean labels are available. However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test…

The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the…

High-quality labeled data is essential to successfully train supervised machine learning models. Although a large amount of unlabeled data is present in the medical domain, labeling poses a major challenge: medical professionals who can…

Semi-supervised anomaly detection, which aims to improve the anomaly detection performance by using a small amount of labeled anomaly data in addition to unlabeled data, has attracted attention. Existing semi-supervised approaches assume…

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…