@inproceedings{qi2026generalizing,
author = {Qi, Daiqing and Zhao, H and Zhang, A and Li, S},
title = {Generalizing (CLIP) to Unseen Domains via Text-guided Augmentation},
booktitle = {European Conference on Computer Vision (ECCV)},
year = {2026},
month = {August},
abstract = {To avoid the high cost of collecting visual data from all test domains in the domain adaptation task, recent work takes advantage of the pre-trained large-scale vision language models and augment training data with only text descriptions (e.g.,“a photo/painting/sketch...”) of each test domain. However, in many real-world applications, such text information of test domains is not always available in advance. Moreover, even if we can verbalize all test domains, it is laborious for existing work [3] to train a different augmentation network for each possible unseen domain, which suffers from time-inefficiency. To overcome these challenges, we benefit from the multimodal embedding space of a pre-trained vision-language model and propose to acquire training-free and domain-invariant augmentations with text descriptions of arbitrary crafted unseen domains, which not necessarily match test domains. Beyond achieving state-of-the-art results, compared with existing works that require trainable augmentation networks, our approach is also notably more time-efficient, and exhibits a more solid theoretical support.},
url = {http://approjects.co.za/?big=en-us/research/publication/generalizing-clip-to-unseen-domains-via-text-guided-augmentation/},
}