{"type":"ScholarlyArticle","title":"ProMEA: Prompt-driven Expansion and Alignment for Single Domain Generalization","authors":[{"name":"Yunyun Wang","slug":"yunyun-wang","given":"Yunyun","family":"Wang","affiliation":""},{"name":"Yi Guo","slug":"yi-guo","given":"Yi","family":"Guo","affiliation":""},{"name":"Xiaodong Liu","slug":"xiaodong-liu","given":"Xiaodong","family":"Liu","affiliation":""},{"name":"Songcan Chen","slug":"songcan-chen","given":"Songcan","family":"Chen","affiliation":""}],"abstract":"In single Domain Generalization (single-DG), data scarcity in the single source domain hampers the learning for invariant features, leading to overfitting over source domain and poor generalization to unseen target domains. Existing single-DG methods primarily augment the source domain by adversarial generation. However, there are still two key challenges. i) With simple feature perturbation to confuse the classifier, it may generate unnatural samples with semantic ambiguity or distortion. ii) It is still difficult to cover the sufficient shift in a real domain by generating indistinguishable samples from source data, thus the learning model is inescapable from overfitting to the single source domain. To this end, we turn to augment the domain prompt, considering that text prompt perturbation is easier to generate and generalize. \r\nThen the source domain is expanded with the guidance of augmented text prompts, which are learnable with both semantic consistency and style diversity. Specifically, we propose a ProMpt-driven Expansion and Alignment (ProMEA) method for single-DG, in which a Domain Prompt Expansion module is first developed to expand the single source domain with frequency features of augmented text prompts, in which the amplitude spectrum predominantly harbors the domain style information. With source prompts, a Domain Prompt Alignment module is further designed in inference for adapting target samples to the expanded source domains, in order to reduce the domain discrepancy. Finally, empirically results over single-DG benchmarks demonstrate the superiority of our proposal.","doi":"10.24963/ijcai.2025/225","url":"https://ijcai.org/proceedings/2025/225","pdf":"https://ijcai.org/proceedings/2025/0225.pdf","markdown":"https://ijcai.org/proceedings/2025/225.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/225","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":225,"pages":{"first":2018,"last":2026},"keywords":["Computer Vision: CV: Transfer, low-shot, semi- and un- supervised learning","Computer Vision: CV: Machine learning for vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}