Long Tail Learning On Places Lt

المقاييس

Top-1 Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

		Paper Title
LIFT (ViT-L/14)	53.7	Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
LIFT (ViT-B/16)	52.2	Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
MAM (ViT-B/16)	51.4	Improving Image Recognition by Retrieving from Web-Scale Image-Text Data
VL-LTR (ViT-B-16)	50.1	VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
BALLAD(ViT-B-16)	49.5	A Simple Long-Tailed Recognition Baseline via Vision-Language Model
BALLAD(ResNet-50×16)	49.3	A Simple Long-Tailed Recognition Baseline via Vision-Language Model
VL-LTR (ResNet-50)	48.0	VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
BALLAD(ResNet-101)	47.9	A Simple Long-Tailed Recognition Baseline via Vision-Language Model
RAC (ViT-B-16)	47.17	Retrieval Augmented Classification for Long-Tail Visual Recognition
BALLAD(ResNet-50)	46.5	A Simple Long-Tailed Recognition Baseline via Vision-Language Model
APA (SE-ResNet-50)	42.0	Adaptive Parametric Activation
GPaCo (ResNet-152)	41.7	Generalized Parametric Contrastive Learning
Difficulty-Net (ResNet-152)	41.7	Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition
NCL(ResNet-152)	41.5	Nested Collaborative Learning for Long-Tailed Visual Recognition
TADE	41.3	Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
PaCo	41.2	Parametric Contrastive Learning
OPeN (ResNet-152)	40.5	Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images
IEM	39.7	Inflated Episodic Memory With Region Self-Attention for Long-Tailed Visual Recognition
DisAlign	39.3	Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
LDAM-DRS-RSG	39.3	RSG: A Simple but Effective Module for Learning Imbalanced Datasets

0 of 29 row(s) selected.

Command Palette

Long Tail Learning On Places Lt

المقاييس

النتائج