image embeddings
Image embeddings are dense vector representations of images that capture semantic features, allowing models to effectively compare and retrieve images based on learned characteristics.
- CellCLIP - Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning
- Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval
- LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
- QuARI: Query Adaptive Retrieval Improvement
- Rare Text Semantics Were Always There in Your Diffusion Transformer
- Training-free Detection of AI-generated images via Cropping Robustness