相关论文: DivideMix: Learning with Noisy Labels as Semi-supe…

Active learning aims to select samples to be annotated that yield the largest performance improvement for the learning algorithm. Many methods approach this problem by measuring the informativeness of samples and do this based on the…

Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc. are gaining increasing importance. Of the different approaches proposed, supervised methods usually give significant…

Semi-supervised learning methods are usually employed in the classification of data sets where only a small subset of the data items is labeled. In these scenarios, label noise is a crucial issue, since the noise may easily spread to a…

Training with noisy class labels impairs neural networks' generalization performance. In this context, mixup is a popular regularization technique to improve training robustness by making memorizing false class labels more difficult.…

To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…

Obtaining pixel-level annotations in the medical domain is both expensive and time-consuming, often requiring close collaboration between clinical experts and developers. Semi-supervised medical image segmentation aims to leverage limited…

Semi-Supervised Learning (SSL) algorithms have shown great potential in training regimes when access to labeled data is scarce but access to unlabeled data is plentiful. However, our experiments illustrate several shortcomings that prior…

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world…

Deep neural networks (DNNs) have achieved great success in a wide variety of medical image analysis tasks. However, these achievements indispensably rely on the accurately-annotated datasets. If with the noisy-labeled images, the training…

Supervised learning, especially supervised deep learning, requires large amounts of labeled data. One approach to collect large amounts of labeled data is by using a crowdsourcing platform where numerous workers perform the annotation…

Contrastive learning has shown outstanding performances in both supervised and unsupervised learning, and has recently been introduced to solve weakly supervised learning problems such as semi-supervised learning and noisy label learning.…

We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by…

Federated learning (FL) is a distributed framework for collaboratively training with privacy guarantees. In real-world scenarios, clients may have Non-IID data (local class imbalance) with poor annotation quality (label noise). The…

Retail scenes usually contain densely packed high number of objects in each image. Standard object detection techniques use fully supervised training methodology. This is highly costly as annotating a large dense retail object detection…

Semi-supervised learning methods are motivated by the availability of large datasets with unlabeled features in addition to labeled data. Unlabeled data is, however, not guaranteed to improve classification performance and has in fact been…

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…

Federated learning is a paradigm that enables local devices to jointly train a server model while keeping the data decentralized and private. In federated learning, since local data are collected by clients, it is hardly guaranteed that the…

Labeling real-world datasets is time consuming but indispensable for supervised machine learning models. A common solution is to distribute the labeling task across a large number of non-expert workers via crowd-sourcing. Due to the varying…

The traditional process of creating labeled datasets is labor-intensive and expensive. Recent breakthroughs in open-source large language models (LLMs) have opened up a new avenue in generating labeled datasets automatically for various…

Labeled data is a critical resource for training and evaluating machine learning models. However, many real-life datasets are only partially labeled. We propose a semi-supervised machine learning training strategy to improve event detection…