Related papers: CLIP-Powered Domain Generalization and Domain Adap…

Although open-vocabulary classification models like Contrastive Language Image Pretraining (CLIP) have demonstrated strong zero-shot learning capabilities, their robustness to common image corruptions remains poorly understood. Through…

Despite the recent progress in incremental learning, addressing catastrophic forgetting under distributional drift is still an open and important problem. Indeed, while state-of-the-art domain incremental learning (DIL) methods perform…

Multi-Source Domain Generalization (DG) is the task of training on multiple source domains and achieving high classification performance on unseen target domains. Recent methods combine robust features from web-scale pretrained backbones…

Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is an increasing need…

Domain adaptation (DA) is a statistical learning problem that arises when the distribution of the source data used to train a model differs from that of the target data used to evaluate the model. While many DA algorithms have demonstrated…

Universal visual anomaly detection aims to identify anomalies from novel or unseen vision domains without additional fine-tuning, which is critical in open scenarios. Recent studies have demonstrated that pre-trained vision-language models…

Domain adaptation (DA) is the task of classifying an unlabeled dataset (target) using a labeled dataset (source) from a related domain. The majority of successful DA methods try to directly match the distributions of the source and target…

Domain adaptation (DA) has drawn high interests for its capacity to adapt a model trained on labeled source data to perform well on unlabeled or weakly labeled target data from a different domain. Most common DA techniques require the…

Contrastive language-image pretraining (CLIP) links vision and language modalities into a unified embedding space, yielding the tremendous potential for vision-language (VL) tasks. While early concurrent works have begun to study this…

The recent advancements in Generative Adversarial Networks (GANs) and the emergence of Diffusion models have significantly streamlined the production of highly realistic and widely accessible synthetic content. As a result, there is a…

Recent 3D generative models have achieved remarkable performance in synthesizing high resolution photorealistic images with view consistency and detailed 3D shapes, but training them for diverse domains is challenging since it requires…

Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an important class of solutions to this problem. Despite their…

Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various architectures, from vision transformers (ViTs) to convolutional networks (ResNets) have been trained with CLIP to…

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…

Foundation models (e.g., CLIP or DINOv2) have shown their impressive learning and transfer capabilities in a wide range of visual tasks, by training on a large corpus of data and adapting to specific downstream tasks. It is, however,…

Domain adaptation (DA) aims to generalize a learning model across training and testing data despite the mismatch of their data distributions. In light of a theoretical estimation of upper error bound, we argue in this paper that an…

Contrastive learning has emerged as an efficient framework to learn multimodal representations. CLIP, a seminal work in this area, achieved impressive results by training on paired image-text data using the contrastive loss. Recent work…

There is a strong incentive to develop versatile learning techniques that can transfer the knowledge of class-separability from a labeled source domain to an unlabeled target domain in the presence of a domain-shift. Existing domain…

Recent approaches leveraging multi-modal pre-trained models like CLIP for Unsupervised Domain Adaptation (UDA) have shown significant promise in bridging domain gaps and improving generalization by utilizing rich semantic knowledge and…

Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance…