Problem
Research questions and friction points this paper is trying to address.
domain adaptation
semantic relationship
distribution shift
SPACE: Semantic Projection and Alignment of CLIP Embeddings for Domain Adaptation
🤖 AI Summary
本文提出SPACE方法，利用CLIP的视觉-语言空间中的语义结构解决领域适应问题，通过文本描述作为语义锚点对齐图像的意义而非外观。
📝 Abstract
A fundamental challenge in deploying vision models is domain shift, which arises when training and test data follow different distributions, leading to degraded performance. This challenge is amplified when the same semantic concept appears under distinct visual forms, such as photographs and sketches, where visual similarity is weak despite semantic correspondence. Existing unsupervised domain-adaptation methods aim to align distributions across domains but often ignore semantic relationships among samples of the same class. To address this issue, this paper introduces SPACE, a method that exploits the semantic structure of CLIP's vision-language space for domain adaptation. The key idea is to use text descriptions as semantic anchors by applying Singular Value Decomposition to CLIP embeddings of class descriptions, yielding an orthogonal basis that captures semantic relationships among categories. Visual features from both domains are projected into this semantic subspace, aligning images based on meaning rather than appearance.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Semantic Projection
CLIP Embeddings
Domain Adaptation
Singular Value Decomposition
🔎 Similar Papers
No similar papers found.
