MobileCLIP: Fast Image-Text Models Through Multi-Modal Reinforced Trainingarxiv.org·1 pts·zerojames·0
Florence-2: Advancing a Unified Representation for a Variety of Vision Tasksarxiv.org·1 pts·zerojames·0
CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Detectionarxiv.org·2 pts·zerojames·0