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

العربية

Image Classification On Dtd

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Accuracy	Paper Title	Repository
SEER (RegNet10B - linear eval)	80.5	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
TWIST (ResNet-50)	76.6	Self-Supervised Learning by Estimating Twin Class Distributions	-
µ2Net (ViT-L/16)	81.0	An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems
TransBoost-ResNet50	76.49	TransBoost: Improving the Best ImageNet Performance using Deep Transduction
NNCLR	75.5	With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
RADAM (ConvNeXt-L)	84.0	RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps
µ2Net+ (ViT-L/16)	82.23	A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems
Bamboo (ViT-B/16)	81.9	Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
Linear FT(ViT-L/14)	90.0	Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
Inceptionv4	79.79	Non-binary deep transfer learning for image classification
Inceptionv4 (random initialization)	66.8	Non-binary deep transfer learning for image classification

0 of 11 row(s) selected.