AI RESEARCH
CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval
arXiv CS.CV
•
ArXi:2601.03728v2 Announce Type: replace Composed Image Retrieval (CIR) enables users to search for target images using both a reference image and manipulation text, offering substantial advantages over single-modality retrieval systems. However, existing CIR methods suffer from representation space fragmentation: queries and targets comprise heterogeneous modalities and are processed by distinct encoders, forcing models to bridge misaligned representation spaces only through post-hoc alignment, which fundamentally limits retrieval performance.