Domain Game: Disentangle Anatomical Feature for Single Domain Generalized Segmentation
원문 초록
Single domain generalization aims to address the challenge of out-of-distribution generalization problem with only one source domain available. Feature distanglement is a classic solution to this purpose, where the extracted task-related feature is presumed to be resilient to domain shift. However, the absence of references from other domains in a single-domain scenario poses significant uncertainty in feature disentanglement (ill-posedness). In this paper, we propose a new framework, named \textit{Domain Game}, to perform better feature distangling for medical image segmentation, based on the observation that diagnostic relevant features are more sensitive to geometric transformations, whilist domain-specific features probably will remain invariant to such operations. In domain game, a set of randomly transformed images derived from a singular source image is strategically encoded into two separate feature sets to represent diagnostic features and domain-specific features, respectively, and we apply forces to pull or repel them in the feature space, accordingly. Results from cross-site test domain evaluation showcase approximately an ~11.8% performance boost in prostate segmentation and around ~10.5% in brain tumor segmentation compared to the second-best method.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
TextBraTS: Text-Guided Volumetric Brain Tumor Segmentation with Innovative Dataset Development and Fusion Module Exploration
C3S3: Complementary Competition and Contrastive Selection for Semi-Supervised Medical Image Segmentation
Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations
Causal-SAM-LLM: Large Language Models as Causal Reasoners for Robust Medical Segmentation
Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization
Segment Anything in Pathology Images with Natural Language
토론
이 논문과 연결된 포럼 글이 아직 없습니다.