Related papers: CDCGen: Cross-Domain Conditional Generation via No…

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not…

Recently, generative adversarial networks (GAN) have gathered a lot of interest. Their efficiency in generating unseen samples of high quality, especially images, has improved over the years. In the field of Natural Language Generation…

This paper strives for domain generalization, where models are trained exclusively on source domains before being deployed on unseen target domains. We follow the strict separation of source training and target testing, but exploit the…

Raman spectroscopy, as a label-free detection technology, has been widely utilized in the clinical diagnosis of pathogenic bacteria. However, Raman signals are naturally weak and sensitive to the condition of the acquisition process. The…

Lack of annotated samples greatly restrains the direct application of deep learning in remote sensing image scene classification. Although researches have been done to tackle this issue by data augmentation with various image transformation…

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…

Domain Generalization (DG) aims to generalize a model trained on multiple source domains to an unseen target domain. The source domains always require precise annotations, which can be cumbersome or even infeasible to obtain in practice due…

Domain alignment refers broadly to learning correspondences between data distributions from distinct domains. In this work, we focus on a setting where domains share underlying structural patterns despite differences in their specific…

A basic assumption of statistical learning theory is that train and test data are drawn from the same underlying distribution. Unfortunately, this assumption doesn't hold in many applications. Instead, ample labeled data might exist in a…

Existing Source-free Unsupervised Domain Adaptation (SUDA) approaches inherently exhibit catastrophic forgetting. Typically, models trained on a labeled source domain and adapted to unlabeled target data improve performance on the target…

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…

In the problem of domain transfer learning, we learn a model for the predic-tion in a target domain from the data of both some source domains and the target domain, where the target domain is in lack of labels while the source domain has…

We do not pursue a novel method in this paper, but aim to study if a modern text-to-image diffusion model can tailor any task-adaptive image classifier across domains and categories. Existing domain adaptive image classification works…

Domain generalization (DG) aims to improve the generalization performance for an unseen target domain by using the knowledge of multiple seen source domains. Mainstream DG methods typically assume that the domain label of each source sample…

Multi-domain image-to-image translation with conditional Generative Adversarial Networks (GANs) can generate highly photo realistic images with desired target classes, yet these synthetic images have not always been helpful to improve…

Domain adaptation is transfer learning which aims to generalize a learning model across training and testing data with different distributions. Most previous research tackle this problem in seeking a shared feature representation between…

The usefulness of deep learning models in robotics is largely dependent on the availability of training data. Manual annotation of training data is often infeasible. Synthetic data is a viable alternative, but suffers from domain gap. We…

We describe a new approach that improves the training of generative adversarial nets (GANs) for synthesizing diverse images from a text input. Our approach is based on the conditional version of GANs and expands on previous work leveraging…

Semantic segmentation models trained on synthetic data often perform poorly on real-world images due to domain gaps, particularly in adverse conditions where labeled data is scarce. Yet, recent foundation models enable to generate realistic…

Unsupervised anomaly detection is a daunting task, as it relies solely on normality patterns from the training data to identify unseen anomalies during testing. Recent approaches have focused on leveraging domain-specific transformations or…