Similar Items: Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification
- DPM++: Dynamic Masked Metric Learning for Occluded Person Re-identification
- DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency
- D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
- AnchorD: Metric Grounding of Monocular Depth Using Factor Graphs
- Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
- Edge-Efficient Image Restoration: Transformer Distillation into State-Space Models