PromptSync: Bridging Domain Gaps in Vision-Language Models through Class-Aware Prototype Alignment and Discrimination
원문 초록
The potential for zero-shot generalization in vision-language (V-L) models such as CLIP has spurred their widespread adoption in addressing numerous downstream tasks. Previous methods have employed test-time prompt tuning to adapt the model to unseen domains, but they overlooked the issue of imbalanced class distributions. In this study, we explicitly address this problem by employing class-aware prototype alignment weighted by mean class probabilities obtained for the test sample and filtered augmented views. Additionally, we ensure that the class probabilities are as accurate as possible by performing prototype discrimination using contrastive learning. The combination of alignment and discriminative loss serves as a geometric regularizer, preventing the prompt representation from collapsing onto a single class and effectively bridging the distribution gap between the source and test domains. Our method, named PromptSync, synchronizes the prompts for each test sample on both the text and vision branches of the V-L model. In empirical evaluations on the domain generalization benchmark, our method outperforms previous best methods by 2.33% in overall performance, by 1% in base-to-novel generalization, and by 2.84% in cross-dataset transfer tasks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Single Domain Generalization for Alzheimer's Detection from 3D MRIs with Pseudo-Morphological Augmentations and Contrastive Learning
Helping CLIP See Both the Forest and the Trees: A Decomposition and Description Approach
FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization
Avoiding Shortcuts: Enhancing Channel-Robust Specific Emitter Identification via Single-Source Domain Generalization
Instance Paradigm Contrastive Learning for Domain Generalization
InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofing
토론
이 논문과 연결된 포럼 글이 아직 없습니다.