Related papers: Training Subset Selection for Weak Supervision
A popular approach to decrease the need for costly manual annotation of large data sets is weak supervision, which introduces problems of noisy labels, coverage and bias. Methods for overcoming these problems have either relied on…
In many machine learning applications, labeling datasets can be an arduous and time-consuming task. Although research has shown that semi-supervised learning techniques can achieve high accuracy with very few labels within the field of…
Supervised learning models often make systematic errors on rare subsets of the data. When these subsets correspond to explicit labels in the data (e.g., gender, race) such poor performance can be identified straightforwardly. This paper…
Sample selection is a prevalent method in learning with noisy labels, where small-loss data are typically considered as correctly labeled data. However, this method may not effectively identify clean hard examples with large losses, which…
Deep networks are successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are usually much less suited for semi-supervised problems because of…
The remarkable success of today's deep neural networks highly depends on a massive number of correctly labeled data. However, it is rather costly to obtain high-quality human-labeled data, leading to the active research area of training…
Modern neural networks have the capacity to overfit noisy labels frequently found in real-world datasets. Although great progress has been made, existing techniques are limited in providing theoretical guarantees for the performance of the…
As machine learning algorithms become increasingly sophisticated to exploit subtle features of the data, they often become more dependent on simulations. This paper presents a new approach called weakly supervised classification in which…
The increasing prominence of weakly labeled data nurtures a growing demand for object detection methods that can cope with minimal supervision. We propose an approach that automatically identifies discriminative configurations of visual…
We propose a novel scalable end-to-end pipeline that uses symbolic domain knowledge as constraints for learning a neural network for classifying unlabeled data in a weak-supervised manner. Our approach is particularly well-suited for…
Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. However, in real-world scenarios, data annotations are often…
Due to the costliness of labelled data in real-world applications, semi-supervised learning, underpinned by pseudo labelling, is an appealing solution. However, handling confusing samples is nontrivial: discarding valuable confusing samples…
This paper discusses the problem of weakly supervised classification, in which instances are given weak labels that are produced by some label-corruption process. The goal is to derive conditions under which loss functions for weak-label…
The growing importance of massive datasets used for deep learning makes robustness to label noise a critical property for classifiers to have. Sources of label noise include automatic labeling, non-expert labeling, and label corruption by…
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…
Weakly supervised text classification methods typically train a deep neural classifier based on pseudo-labels. The quality of pseudo-labels is crucial to final performance but they are inevitably noisy due to their heuristic nature, so…
Improving a semi-supervised image segmentation task has the option of adding more unlabelled images, labelling the unlabelled images or combining both, as neither image acquisition nor expert labelling can be considered trivial in most…
To create a large amount of training labels for machine learning models effectively and efficiently, researchers have turned to Weak Supervision (WS), which uses programmatic labeling sources rather than manual annotation. Existing works of…
Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require…
We present a probabilistic modeling and inference framework for discriminative analysis dictionary learning under a weak supervision setting. Dictionary learning approaches have been widely used for tasks such as low-level signal denoising…