相关论文: P{\O}DA: Prompt-driven Zero-shot Domain Adaptation
The deployment of automated pavement defect detection is often hindered by poor cross-domain generalization. Supervised detectors achieve strong in-domain accuracy but require costly re-annotation for new environments, while standard…
Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it helps deploy on real "target domain" data models that are…
Prompt learning has emerged as a powerful paradigm for adapting vision-language models such as CLIP to downstream tasks. However, existing methods often overfit to seen data, leading to significant performance degradation when generalizing…
Domain adaptation has become a widely adopted approach in machine learning due to the high costs associated with labeling data. It is typically applied when access to a labeled source domain is available. However, in real-world scenarios,…
Unsupervised Domain Adaptation (UDA) can tackle the challenge that convolutional neural network(CNN)-based approaches for semantic segmentation heavily rely on the pixel-level annotated data, which is labor-intensive. However, existing UDA…
Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e.g. achieving 76.3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits…
Recently, Vision-Language foundation models like CLIP and ALIGN, which are pre-trained on large-scale data have shown remarkable zero-shot generalization to diverse datasets with different classes and even domains. In this work, we take a…
Test-time adaptation (TTA) has gained increasing popularity due to its efficacy in addressing ``distribution shift'' issue while simultaneously protecting data privacy. However, most prior methods assume that a paired source domain model…
We present a novel unsupervised domain adaptation method for semantic segmentation that generalizes a model trained with source images and corresponding ground-truth labels to a target domain. A key to domain adaptive semantic segmentation…
Zero-shot anomaly detection (ZSAD) targets the identification of anomalies within images from arbitrary novel categories. This study introduces AdaCLIP for the ZSAD task, leveraging a pre-trained vision-language model (VLM), CLIP. AdaCLIP…
Unsupervised Domain Adaptation (UDA) of semantic segmentation transfers labeled source knowledge to an unlabeled target domain by relying on accessing both the source and target data. However, the access to source data is often restricted…
Domain adaptation (DA) paves the way for label annotation and dataset bias issues by the knowledge transfer from a label-rich source domain to a related but unlabeled target domain. A mainstream of DA methods is to align the feature…
Unsupervised domain adaptation is one of the challenging problems in computer vision. This paper presents a novel approach to unsupervised domain adaptations based on the optimal transport-based distance. Our approach allows aligning target…
Domain adaptation (DA) addresses the real-world image classification problem of discrepancy between training (source) and testing (target) data distributions. We propose an unsupervised DA method that considers the presence of only…
Domain adaptation helps transfer the knowledge gained from a labeled source domain to an unlabeled target domain. During the past few years, different domain adaptation techniques have been published. One common flaw of these approaches is…
We explore the zero-shot setting for day-night domain adaptation. The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting unlabeled data samples from the test set. As gathering…
Large vision-language representation learning models like CLIP have demonstrated impressive performance for zero-shot transfer to downstream tasks while largely benefiting from inter-modal (image-text) alignment via contrastive objectives.…
Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., video game, to unlabeled…
Domain adaptation (DA) aims to alleviate the domain shift between source domain and target domain. Most DA methods require access to the source data, but often that is not possible (e.g. due to data privacy or intellectual property). In…
Domain adaptation (DA) techniques help deep learning models generalize across data shifts for point cloud semantic segmentation (PCSS). Test-time adaptation (TTA) allows direct adaptation of a pre-trained model to unlabeled data during…