PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
- Title
- PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
- Authors
- Cho, Junhyeong; Nam, Gilhyun; 김성연; Yang, Hunmin; 곽수하
- Date Issued
- 2023-10
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Abstract
- In a joint vision-language space, a text feature (e.g., from "a photo of a dog") could effectively represent its relevant image features (e.g., from dog photos). Also, a recent study has demonstrated the cross-modal transferability phenomenon of this joint space. From these observations, we propose PromptStyler which simulates various distribution shifts in the joint space by synthesizing diverse styles via prompts without using any images to deal with source-free domain generalization. The proposed method learns to generate a variety of style features (from "a S
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/122805
- Article Type
- Conference
- Citation
- 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023, page. 15656 - 15666, 2023-10
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.