Improving Source-Free Target Adaptation with Vision Transformers Leveraging Domain Representation Images
원문 초록
Unsupervised Domain Adaptation (UDA) methods facilitate knowledge transfer from a labeled source domain to an unlabeled target domain, navigating the obstacle of domain shift. While Convolutional Neural Networks (CNNs) are a staple in UDA, the rise of Vision Transformers (ViTs) provides new avenues for domain generalization. This paper presents an innovative method to bolster ViT performance in source-free target adaptation, beginning with an evaluation of how key, query, and value elements affect ViT outcomes. Experiments indicate that altering the key component has negligible effects on Transformer performance. Leveraging this discovery, we introduce Domain Representation Images (DRIs), feeding embeddings through the key element. DRIs act as domain-specific markers, effortlessly merging with the training regimen. To assess our method, we perform target adaptation tests on the Cross Instance DRI source-only (SO) control. We measure the efficacy of target adaptation with and without DRIs, against existing benchmarks like SHOT-B* and adaptations via CDTrans. Findings demonstrate that excluding DRIs offers limited gains over SHOT-B*, while their inclusion in the key segment boosts average precision promoting superior domain generalization. This research underscores the vital role of DRIs in enhancing ViT efficiency in UDA scenarios, setting a precedent for further domain adaptation explorations.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation
Learning Generalized Segmentation for Foggy-scenes by Bi-directional Wavelet Guidance
Multiview Contrastive Learning for Unsupervised Domain Adaptation in Brain–Computer Interfaces
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition
Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.