الرئيسية الأخبار أحدث الأوراق البحثية الدروس مجموعات البيانات الموسوعة SOTA نماذج LLM لوحة الأداء GPU الفعاليات

العربية

Zero Shot Transfer Image Classification On 3

المقاييس

Accuracy (Private)

Accuracy (Public)

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Accuracy (Private)	Accuracy (Public)	Paper Title	Repository
LiT-tuning	78.7	66.6	LiT: Zero-Shot Transfer with Locked-image text Tuning	-
InternVL-C	77.3	-	InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks	-
PaLI	64.46	-	PaLI: A Jointly-Scaled Multilingual Language-Image Model	-
CoCa	80.7	-	CoCa: Contrastive Captioners are Image-Text Foundation Models	-
AltCLIP	68.1	-	AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities	-
LiT ViT-e	80.6	-	PaLI: A Jointly-Scaled Multilingual Language-Image Model	-
ALIGN	70.1	-	Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision	-
EVA-CLIP-E/14+	75.7	-	EVA-CLIP: Improved Training Techniques for CLIP at Scale	-
BASIC (Lion)	81.2	-	-	-
EVA-CLIP-18B	77.9	-	EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters	-
LiT-22B	80.9	-	Scaling Vision Transformers to 22 Billion Parameters	-
BASIC	80.6	-	Combined Scaling for Zero-shot Transfer Learning	-
CLIP	70.1	-	Learning Transferable Visual Models From Natural Language Supervision	-

0 of 13 row(s) selected.