HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Long Tail Learning On Imagenet Lt

Metrics

Top-1 Accuracy

Results

Performance results of various models on this benchmark

Paper TitleRepository
LIFT (ViT-L/14)82.9Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
µ2Net+ (ViT-L/16)82.5A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems
MAM (ViT-B/16)82.3Improving Image Recognition by Retrieving from Web-Scale Image-Text Data-
LIFT (ViT-B/16)78.3Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
VL-LTR (ViT-B-16)77.2VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
BALLAD(ResNet-50×16)76.5A Simple Long-Tailed Recognition Baseline via Vision-Language Model
BALLAD(ViT-B-16)75.7A Simple Long-Tailed Recognition Baseline via Vision-Language Model
BALLAD(ResNet-101)70.5A Simple Long-Tailed Recognition Baseline via Vision-Language Model
VL-LTR (ResNet-50)70.1VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
BALLAD(ResNet-50)67.2A Simple Long-Tailed Recognition Baseline via Vision-Language Model
GPaCo (2-ResNeXt101-32x4d)63.2Generalized Parametric Contrastive Learning
MDCS (ResNeXt-50)61.8MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition
TADE(ResNeXt101-32x4d)61.4Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
ProCo (ResNet50)60.2Probabilistic Contrastive Learning for Long-Tailed Visual Recognition
PaCo(ResNeXt101-32x4d)60.0Parametric Contrastive Learning
DeiT-LT59.1DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
APA (SE-ResNext-50)59.1Adaptive Parametric Activation
TADE(ResNeXt-50)58.8Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
GML (ResNeXt-50)58.8Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
DirMixE(ResNeXt-50)58.61Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition
0 of 69 row(s) selected.