SOTAVerified

Multi-Label Image Classification

The Multi-Label Image Classification focuses on predicting labels for images in a multi-class classification problem where each image may belong to more than one class.

Papers

Showing 110 of 124 papers

TitleStatusHype
Domain Adaptation for Multi-label Image Classification: a Discriminator-free ApproachCode1
Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning0
Multi-label Classification using Deep Multi-order Context-aware Kernel Networks0
When the Small-Loss Trick is Not Enough: Multi-Label Image Classification with Noisy Labels Applied to CCTV Sewer Inspections0
Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image ClassificationCode1
HSVLT: Hierarchical Scale-Aware Vision-Language Transformer for Multi-Label Image Classification0
Multi-Label Plant Species Classification with Self-Supervised Vision TransformersCode1
Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributes0
reBEN: Refined BigEarthNet Dataset for Remote Sensing Image AnalysisCode1
Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels0
Show:102550
← PrevPage 1 of 13Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MoCo-v2 (ResNet50, fine tune)mAP (micro)91.8Unverified
2MoCo-v3 (ViT-S/16, fine tune)mAP (micro)89.9Unverified
3MoCo-v2 (ResNet18, fine tune)mAP (micro)89.3Unverified
4MAE (ViT-S/16, fine tune)mAP (micro)88.9Unverified
5DINO-MCmAP (micro)88.75Unverified
6WideResNet-B5-ECAFScore79Unverified
7ViTM/20FScore77.1Unverified
8ResNet50FScore76.8Unverified
9ResNet50mAP (macro)75.36Unverified
10MLPMixerFScore75.2Unverified