Related papers: Meta Learning on a Sequence of Imbalanced Domains …

Rehearsal, seeking to remind the model by storing old knowledge in lifelong learning, is one of the most effective ways to mitigate catastrophic forgetting, i.e., biased forgetting of previous knowledge when moving to new tasks. However,…

Data collection and annotation are time-consuming in machine learning, expecially for large scale problem. A common approach for this problem is to transfer knowledge from a related labeled domain to a target one. There are two popular ways…

Domain adaptation seeks to leverage the abundant label information in a source domain to improve classification performance in a target domain with limited labels. While the field has seen extensive methodological development, its…

The computer vision community is witnessing an unprecedented rate of new tasks being proposed and addressed, thanks to the deep convolutional networks' capability to find complex mappings from X to Y. The advent of each task often…

In this paper, we propose a learning algorithm that enables a model to quickly exploit commonalities among related tasks from an unseen task distribution, before quickly adapting to specific tasks from that same distribution. We investigate…

Contrastive learning is among the most popular and powerful approaches for self-supervised representation learning, where the goal is to map semantically similar samples close together while separating dissimilar ones in the latent space.…

Unsupervised domain adaptation (UDA) is a statistical learning problem when the distribution of training (source) data is different from that of test (target) data. In this setting, one has access to labeled data only from the source domain…

Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. Though deep learning and adversarial strategy make an important breakthrough in the adaptability of…

Unsupervised domain adaptation aims to learn a model of classifier for unlabeled samples on the target domain, given training data of labeled samples on the source domain. Impressive progress is made recently by learning invariant features…

Domain generalization (DG) is a fundamental yet very challenging research topic in machine learning. The existing arts mainly focus on learning domain-invariant features with limited source domains in a static model. Unfortunately, there is…

In this paper, we aim to adapt a model at test-time using a few unlabeled data to address distribution shifts. To tackle the challenges of extracting domain knowledge from a limited amount of data, it is crucial to utilize correlated…

Meta-learning models transfer the knowledge acquired from previous tasks to quickly learn new ones. They are trained on benchmarks with a fixed number of data points per task. This number is usually arbitrary and it is unknown how it…

Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source…

Semantic segmentation is a fundamental computer vision task with a vast number of applications. State of the art methods increasingly rely on deep learning models, known to incorrectly estimate uncertainty and being overconfident in…

Training of deep neural networks heavily depends on the data distribution. In particular, the networks easily suffer from class imbalance. The trained networks would recognize the frequent classes better than the infrequent classes. To…

Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose a method for…

A novel approach for unsupervised domain adaptation for neural networks is proposed. It relies on metric-based regularization of the learning process. The metric-based regularization aims at domain-invariant latent feature representations…

A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. However, this assumption is violated in almost all practical applications: machine learning…

In this work, we analyze the conditions under which information about the context of an input $X$ can improve the predictions of deep learning models in new domains. Following work in marginal transfer learning in Domain Generalization…

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…