Related papers: Disjoint Contrastive Regression Learning for Multi…

Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…

Many machine learning systems today are trained on large amounts of human-annotated data. Data annotation tasks that require a high level of competency make data acquisition expensive, while the resulting labels are often subjective,…

Current contrastive learning methods use random transformations sampled from a large list of transformations, with fixed hyperparameters, to learn invariance from an unannotated database. Following previous works that introduce a small…

International audit standards require the direct assessment of a financial statement's underlying accounting transactions, referred to as journal entries. Recently, driven by the advances in artificial intelligence, deep learning inspired…

Contrastive learning methods enforce label distance relationships in feature space to improve representation capability for regression models. However, these methods highly depend on label information to correctly recover ordinal…

Deep neural networks (DNNs) have been widely applied in medical image classification and achieve remarkable classification performance. These achievements heavily depend on large-scale accurately annotated training data. However, label…

In multi-label learning, leveraging contrastive learning to learn better representations faces a key challenge: selecting positive and negative samples and effectively utilizing label information. Previous studies selected positive and…

We propose a meta-learning method for learning from multiple noisy annotators. In many applications such as crowdsourcing services, labels for supervised learning are given by multiple annotators. Since the annotators have different skills…

How can you sample good negative examples for contrastive learning? We argue that, as with metric learning, contrastive learning of representations benefits from hard negative samples (i.e., points that are difficult to distinguish from an…

Supervised training of object detectors requires well-annotated large-scale datasets, whose production is costly. Therefore, some efforts have been made to obtain annotations in economical ways, such as cloud sourcing. However, datasets…

Learning from multiple annotators aims to induce a high-quality classifier from training instances, where each of them is associated with a set of possibly noisy labels provided by multiple annotators under the influence of their varying…

Recently, contrastive self-supervised learning has become a key component for learning visual representations across many computer vision tasks and benchmarks. However, contrastive learning in the context of domain adaptation remains…

Labelled data is the foundation of most natural language processing tasks. However, labelling data is difficult and there often are diverse valid beliefs about what the correct data labels should be. So far, dataset creators have…

Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent…

Supervised classification algorithms are used to solve a growing number of real-life problems around the globe. Their performance is strictly connected with the quality of labels used in training. Unfortunately, acquiring good-quality…

For the Facial Action Unit (AU) detection task, accurately capturing the subtle facial differences between distinct AUs is essential for reliable detection. Additionally, AU detection faces challenges from class imbalance and the presence…

Since state-of-the-art approaches to offensive language detection rely on supervised learning, it is crucial to quickly adapt them to the continuously evolving scenario of social media. While several approaches have been proposed to tackle…

Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant…

Training a deep neural network heavily relies on a large amount of training data with accurate annotations. To alleviate this problem, various methods have been proposed to annotate the data automatically. However, automatically generating…

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…