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

العربية

Long Tail Learning On Coco Mlt

المقاييس

Average mAP

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Average mAP	Paper Title	Repository
DB Focal(ResNet-50)	53.55	Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
PG Loss(ResNet-50)	54.43	Probability Guided Loss for Long-Tailed Multi-Label Image Classification	-
LDAM(ResNet-50)	40.53	Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
RS(ResNet-50)	46.97	Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks
ML-GCN(ResNet-50)	44.24	Multi-Label Image Recognition with Graph Convolutional Networks
Focal Loss(ResNet-50)	49.46	Focal Loss for Dense Object Detection
LMPT(ResNet-50)	58.97	LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition
OLTR(ResNet-50)	45.83	Large-Scale Long-Tailed Recognition in an Open World
LTML(ResNet-50)	56.90	Long-Tailed Multi-Label Visual Recognition by Collaborative Training on Uniform and Re-Balanced Samplings	-
CB Loss(ResNet-50)	49.06	Class-Balanced Loss Based on Effective Number of Samples
CLIP(ViT-B/16)	60.17	Learning Transferable Visual Models From Natural Language Supervision
CLIP(ResNet-50)	56.19	Learning Transferable Visual Models From Natural Language Supervision
LMPT(ViT-B/16)	66.19	LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition

0 of 13 row(s) selected.