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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–124 of 124 papers

TitleStatusHype
Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers—0
Unified smoke and fire detection in an evolutionary framework with self-supervised progressive data augment—0
Unsupervised domain adaptation by learning using privileged information—0
Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization—0
In-domain representation learning for remote sensingCode0
SoDeep: a Sorting Deep net to learn ranking loss surrogatesCode0
Visual Attention Consistency Under Image Transforms for Multi-Label Image ClassificationCode0
Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based TrainingCode0
SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image ClassificationCode0
ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual ClassificationCode0
Improving Pairwise Ranking for Multi-label Image ClassificationCode0
Plot2API: Recommending Graphic API from Plot via Semantic Parsing Guided Neural NetworkCode0
Structured Label Inference for Visual UnderstandingCode0
PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image ClassificationCode0
Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model BiasCode0
ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image DatasetCode0
CNN-RNN: A Unified Framework for Multi-label Image ClassificationCode0
A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural NetworksCode0
SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial ImagesCode0
Multi-relation Message Passing for Multi-label Text ClassificationCode0
Learning Spatial Regularization with Image-level Supervisions for Multi-label Image ClassificationCode0
Unsupervised Image Classification for Deep Representation LearningCode0
Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing LabelsCode0
Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and BenchmarkCode0
Show:102550
← PrevPage 3 of 3Next →
All datasetsBigEarthNetBigEarthNet (official test set)MSCOCOBigEarthNet-S1 (official test set)BigEarthNet-10%VizWiz-ClassificationVOC2007

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MoCo-v2 (ResNet50, fine tune)mAP (micro)91.8—Unverified
2MoCo-v3 (ViT-S/16, fine tune)mAP (micro)89.9—Unverified
3MoCo-v2 (ResNet18, fine tune)mAP (micro)89.3—Unverified
4MAE (ViT-S/16, fine tune)mAP (micro)88.9—Unverified
5DINO-MCmAP (micro)88.75—Unverified
6WideResNet-B5-ECAFScore79—Unverified
7ViTM/20FScore77.1—Unverified
8ResNet50FScore76.8—Unverified
9ResNet50mAP (macro)75.36—Unverified
10MLPMixerFScore75.2—Unverified
#ModelMetricClaimedVerifiedStatus
1FG-MAE (ViT-S/16)mAP (micro)89.3—Unverified
2MoCov3 (ViT-S/16)mAP (micro)89.3—Unverified
3MoCov2 (ResNet50)mAP (micro)88.7—Unverified
4MAE (ViT-S/16)mAP (micro)88.6—Unverified
5ViT-S/16mAP (micro)87.8—Unverified
6ResNet50F1 Score76.8—Unverified
#ModelMetricClaimedVerifiedStatus
1IDA-SwinL(H) 384mAP90.3—Unverified
2ML-AGCNmean average precision86.9—Unverified
3IDA-R101(H) 576mAP86.3—Unverified
4IDA-R101(H)mAP84.8—Unverified
#ModelMetricClaimedVerifiedStatus
1FG-MAE (ViT-S/16)mAP (micro)82.7—Unverified
2MAE (ViT-S/16)mAP (micro)81.3—Unverified
3ViT-S/16mAP (micro)79.5—Unverified
#ModelMetricClaimedVerifiedStatus
1DINO-MCmean average precision84.2—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet151Accuracy47.5—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet101MAP96.8—Unverified