Open Vocabulary Attribute Detection On Ovad 1

المقاييس

mean average precision

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

		Paper Title
X-VLM	28.0	Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
BLIP 2 (pretrained)	25.5	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP	24.3	BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
OVAD-Baseline-Box	21.4	Open-vocabulary Attribute Detection
ALBEF	21.0	Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
Open CLIP ViT-B32	17.0	Reproducible scaling laws for contrastive language-image learning
CLIP VIT-B16	16.6	Learning Transferable Visual Models From Natural Language Supervision

0 of 7 row(s) selected.

Open Vocabulary Attribute Detection On Ovad 1 | SOTA | HyperAI