Extending CLIP's Image-Text Alignment to Referring Image Segmentation
원문 초록
Referring Image Segmentation (RIS) is a cross-modal task that aims to segment an instance described by a natural language expression. Recent methods leverage large-scale pretrained unimodal models as backbones along with fusion techniques for joint reasoning across modalities. However, the inherent cross-modal nature of RIS raises questions about the effectiveness of unimodal backbones. We propose RISCLIP, a novel framework that effectively leverages the cross-modal nature of CLIP for RIS. Observing CLIP's inherent alignment between image and text features, we capitalize on this starting point and introduce simple but strong modules that enhance unimodal feature extraction and leverage rich alignment knowledge in CLIP's image-text shared-embedding space. RISCLIP exhibits outstanding results on all three major RIS benchmarks and also outperforms previous CLIP-based methods, demonstrating the efficacy of our strategy in extending CLIP's image-text alignment to RIS.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy
Semantic Localization Guiding Segment Anything Model For Reference Remote Sensing Image Segmentation
Refer to Anything with Vision-Language Prompts
Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation
U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV
A New Dataset and Performance Benchmark for Real-time Spacecraft Segmentation in Onboard Flight Computers
토론
이 논문과 연결된 포럼 글이 아직 없습니다.