Related papers: SHED: Style-Homogenized Embedding Alignment for Do…

Large-scale foundation models, such as CLIP, have demonstrated impressive zero-shot generalization performance on downstream tasks, leveraging well-designed language prompts. However, these prompt learning techniques often struggle with…

CLIP-based domain generalization aims to improve model generalization to unseen domains by leveraging the powerful zero-shot classification capabilities of CLIP and multiple source datasets. Existing methods typically train a single model…

Large-scale foundation models like CLIP have shown strong zero-shot generalization but struggle with domain shifts, limiting their adaptability. In our work, we introduce \textsc{StyLIP}, a novel domain-agnostic prompt learning strategy for…

Domain generalization studies the problem of training a model with samples from several domains (or distributions) and then testing the model with samples from a new, unseen domain. In this paper, we propose a novel approach for domain…

Domain Generalization (DG), a crucial research area, seeks to train models across multiple domains and test them on unseen ones. In this paper, we introduce a novel approach, namely, Selective Cross-Modality Distillation for Domain…

Domain Generalized Semantic Segmentation (DGSS) seeks to utilize source domain data exclusively to enhance the generalization of semantic segmentation across unknown target domains. Prevailing studies predominantly concentrate on feature…

The Semantic Layered Embedding Diffusion (SLED) mechanism redefines the representation of hierarchical semantics within transformer-based architectures, enabling enhanced contextual consistency across a wide array of linguistic tasks. By…

Semi-supervised domain adaptation methods leverage information from a source labelled domain with the goal of generalizing over a scarcely labelled target domain. While this setting already poses challenges due to potential distribution…

Domain generalization for semantic segmentation aims to mitigate the degradation in model performance caused by domain shifts. However, in many real-world scenarios, we are unable to access the model parameters and architectural details due…

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…

While deep Embedding Learning approaches have witnessed widespread success in multiple computer vision tasks, the state-of-the-art methods for representing natural images need not necessarily perform well on images from other domains, such…

Unsupervised domain adaption (UDA) has emerged as a popular solution to tackle the divergence between the labeled source and unlabeled target domains. Recently, some research efforts have been made to leverage large vision-language models,…

Domain shift widely exists in the visual world, while modern deep neural networks commonly suffer from severe performance degradation under domain shift due to the poor generalization ability, which limits the real-world applications. The…

Domain generalization (DG) aims to learn a model from source domains and apply it to unseen target domains with out-of-distribution data. Owing to CLIP's strong ability to encode semantic concepts, it has attracted increasing interest in…

Domain generalization is the task of learning models that generalize to unseen target domains. We propose a simple yet effective method for domain generalization, named cross-domain ensemble distillation (XDED), that learns domain-invariant…

Given unlabelled datasets containing both old and new categories, generalized category discovery (GCD) aims to accurately discover new classes while correctly classifying old classes. Current GCD methods only use a single visual modality of…

Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. While this has been well studied for image classification, the literature on SDG object…

Single source domain generalization (SDG) holds promise for more reliable and consistent image segmentation across real-world clinical settings particularly in the medical domain, where data privacy and acquisition cost constraints often…

Generalization to new domains not seen during training is one of the long-standing challenges in deploying neural networks in real-world applications. Existing generalization techniques either necessitate external images for augmentation,…

We focus on domain and class generalization problems in analyzing optical remote sensing images, using the large-scale pre-trained vision-language model (VLM), CLIP. While contrastively trained VLMs show impressive zero-shot generalization…