Clustering-based Image-Text Graph Matching for Domain Generalization

arXiv:2310.02692v2 Announce Type: replace
Abstract: Learning domain-invariant visual representations is important to train a model that can generalize well to unseen target task domains. Recent works demonstrate that text descriptions contain high-level class-discriminative information and such auxiliary semantic cues can be used as effective pivot embedding for domain generalization problem. However, they use pivot embedding in global manner (i.e., aligning an image embedding with sentence-level text embedding), not fully utilizing the semantic cues of given text description. In this work, …

abstract arxiv class clustering cs.ai cs.cv domain domains embedding graph however image information pivot semantic text train type visual