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 51–75 of 124 papers

TitleStatusHype
ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image DatasetCode0
SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial ImagesCode0
Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and BenchmarkCode0
SoDeep: a Sorting Deep net to learn ranking loss surrogatesCode0
SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image ClassificationCode0
Structured Label Inference for Visual UnderstandingCode0
Unsupervised Image Classification for Deep Representation LearningCode0
Visual Attention Consistency Under Image Transforms for Multi-Label Image ClassificationCode0
Learn to Predict Sets Using Feed-Forward Neural Networks—0
Federated Learning Across Decentralized and Unshared Archives for Remote Sensing Image Classification—0
Evaluating the performance of the LIME and Grad-CAM explanation methods on a LEGO multi-label image classification task—0
MS-Twins: Multi-Scale Deep Self-Attention Networks for Medical Image Segmentation—0
Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning—0
Multi-Label Adversarial Perturbations—0
Multi-label Classification using Deep Multi-order Context-aware Kernel Networks—0
Multi-Label Continual Learning for the Medical Domain: A Novel Benchmark—0
Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains—0
Multi Label Image Classification using Adaptive Graph Convolutional Networks (ML-AGCN)—0
Estimating Physical Information Consistency of Channel Data Augmentation for Remote Sensing Images—0
Multi-Label Image Classification with Regional Latent Semantic Dependencies—0
Multi-Label Image Classification with Contrastive Learning—0
Multi-label Image Recognition by Recurrently Discovering Attentional Regions—0
Distance-based Composable Representations with Neural Networks—0
Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model—0
Deep Learning based Multi-Label Image Classification of Protest Activities—0
Show:102550
← PrevPage 3 of 5Next →
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
1MoCov3 (ViT-S/16)mAP (micro)89.3—Unverified
2FG-MAE (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