AI RESEARCH
Geometric Analysis of Self-Supervised Vision Representations for Semantic Image Retrieval
arXiv CS.CV
•
ArXi:2604.24469v1 Announce Type: cross Content-based image retrieval (CBIR) systems enable users to search images based on visual content instead of relying on metadata. The text domain has benefited from vector search of representations created with unsupervised methods such as BERT. However, modern self-supervised learning methods for vision are mostly not reported in CBIR-related literature, instead relying on supervised models or multi-modal methods that align text and vision.