Related papers: PC$^2$: Pseudo-Classification Based Pseudo-Caption…
Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliablility of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an…
Collecting a large number of reliable training images annotated by multiple land-cover class labels in the framework of multi-label classification is time-consuming and costly in remote sensing (RS). To address this problem, publicly…
Label noise widely exists in large-scale datasets and significantly degenerates the performances of deep learning algorithms. Due to the non-identifiability of the instance-dependent noise transition matrix, most existing algorithms address…
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…
Detecting critical transitions in complex, noisy time-series data is a fundamental challenge across science and engineering. Such transitions may be anticipated by the emergence of a low-dimensional order parameter, whose signature is often…
With the widespread use of machine learning for classification, it becomes increasingly important to be able to use weaker kinds of supervision for tasks in which it is hard to obtain standard labeled data. One such kind of supervision is…
This paper considers the problem of unsupervised person re-identification (re-ID), which aims to learn discriminative models with unlabeled data. One popular method is to obtain pseudo-label by clustering and use them to optimize the model.…
Multi-label image classification aims to predict all possible labels in an image. It is usually formulated as a partial-label learning problem, given the fact that it could be expensive in practice to annotate all labels in every training…
In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect labels is…
Topic modelling is a pivotal unsupervised machine learning technique for extracting valuable insights from large document collections. Existing neural topic modelling methods often encode contextual information of documents, while ignoring…
Leveraging the powerful representation learning capabilities, deep multi-view clustering methods have demonstrated reliable performance by effectively integrating multi-source information from diverse views in recent years. Most existing…
Cross-modal retrieval methods build a common representation space for samples from multiple modalities, typically from the vision and the language domains. For images and their captions, the multiplicity of the correspondences makes the…
Learning from noisy labels (LNL) is crucial in deep learning, in which one of the approaches is to identify clean-label samples from poorly-annotated datasets. Such an identification is challenging because the conventional LNL problem,…
The success of Deep Neural Network (DNN) models significantly depends on the quality of provided annotations. In medical image segmentation, for example, having multiple expert annotations for each data point is common to minimize…
Convolutional Neural Networks (CNNs) provide excellent performance when used for image classification. The classical method of training CNNs is by labeling images in a supervised manner as in "input image belongs to this label" (Positive…
Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…
Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could…
Unsupervised visible-infrared person re-identification (UVI-ReID) aims to retrieve pedestrian images across different modalities without costly annotations, but faces challenges due to the modality gap and lack of supervision. Existing…
We tackle the problem of learning linear classifiers from noisy datasets in a multiclass setting. The two-class version of this problem was studied a few years ago by, e.g. Bylander (1994) and Blum et al. (1996): in these contributions, the…
The label noise transition matrix, characterizing the probabilities of a training instance being wrongly annotated, is crucial to designing popular solutions to learning with noisy labels. Existing works heavily rely on finding "anchor…