Related papers: AD-Aligning: Emulating Human-like Generalization f…
Domain-adaptive pre-training (or DA-training for short), also known as post-training, aims to train a pre-trained general-purpose language model (LM) using an unlabeled corpus of a particular domain to adapt the LM so that end-tasks in the…
Classifiers trained on given databases perform poorly when tested on data acquired in different settings. This is explained in domain adaptation through a shift among distributions of the source and target domains. Attempts to align them…
Compressed Deep Learning (DL) models are essential for deployment in resource-constrained environments. But their performance often lags behind their large-scale counterparts. To bridge this gap, we propose Alignment Adapter (AlAd): a…
Unsupervised domain adaptive classifcation intends to improve the classifcation performance on unlabeled target domain. To alleviate the adverse effect of domain shift, many approaches align the source and target domains in the feature…
Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training. Popular domain alignment methods for domain…
Deep learning has emerged as a leading approach for Automatic Modulation Classification (AMC), demonstrating superior performance over traditional methods. However, vulnerability to adversarial attacks and susceptibility to data…
Domain adaptation aims to bridge the domain shifts between the source and the target domain. These shifts may span different dimensions such as fog, rainfall, etc. However, recent methods typically do not consider explicit prior knowledge…
One recent research demonstrated successful application of the label alignment property for unsupervised domain adaptation in a linear regression settings. Instead of regularizing representation learning to be domain invariant, the research…
Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adaptation include: (a) maximizing performance on the target, and…
Deep convolutional neural networks have considerably improved state-of-the-art results for semantic segmentation. Nevertheless, even modern architectures lack the ability to generalize well to a test dataset that originates from a different…
Although deep learning models have shown impressive performance on supervised learning tasks, they often struggle to generalize well when the training (source) and test (target) domains differ. Unsupervised domain adaptation (DA) has…
Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the…
In the presence of large sets of labeled data, Deep Learning (DL) has accomplished extraordinary triumphs in the avenue of computer vision, particularly in object classification and recognition tasks. However, DL cannot always perform well…
We propose Domain-Conditioned Meta-Contrastive Learning, a framework for improving the cross-domain generalization of vision-language models. While contrastive models such as CLIP achieve strong performance through large-scale training,…
Domain adaptation is one of the most crucial techniques to mitigate the domain shift problem, which exists when transferring knowledge from an abundant labeled sourced domain to a target domain with few or no labels. Partial domain…
Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…
We extend semi-supervised learning to the problem of domain adaptation to learn significantly higher-accuracy models that train on one data distribution and test on a different one. With the goal of generality, we introduce AdaMatch, a…
Human beings can quickly adapt to environmental changes by leveraging learning experience. However, adapting deep neural networks to dynamic environments by machine learning algorithms remains a challenge. To better understand this issue,…
Continual domain shift poses a significant challenge in real-world applications, particularly in situations where labeled data is not available for new domains. The challenge of acquiring knowledge in this problem setting is referred to as…
Given datasets from multiple domains, a key challenge is to efficiently exploit these data sources for modeling a target domain. Variants of this problem have been studied in many contexts, such as cross-domain translation and domain…