OpenCodePapers

multi-label-classification-on-chexpert

Multi-Label Classification
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAVERAGE AUC ON 14 LABELNUM RADS BELOW CURVEModelNameReleaseDate
Category-Wise Fine-Tuning for Image Multi-label Classification with Partial Labels✓ Link0.933CFT (ensemble) Macao Polytechnic University2023-11-27
Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification✓ Link0.9302.800DeepAUC-v12020-12-06
Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels✓ Link0.9302.600Hierarchical-Learning-V1 (ensemble)2019-11-15
[]()0.9292.800YWW(ensemble)
[]()0.9292.600Conditional-Training-LSR
Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels✓ Link0.9292.600Hierarchical-Learning-V4 (ensemble)2019-11-15
[]()0.9292.600Conditional-Training-LSR-V1
[]()0.9292.600Hierarchical-Learning-V0 (ensemble)
[]()0.9282.600Multi-Stage-Learning-CNN-V3 (ensemble)
[]()0.9282.600DeepCNNsGM(ensemble)
[]()0.9273.000inisis
[]()0.9272.600DeepCNNs(ensemble)
[]()0.9272.600SenseXDR
[]()0.9272.600ihil (ensemble)
[]()0.9263.000JF aboy ensemble_V2 JF HEALTHCARE https://github.com/deadpoppy/CheXpert-Challeng
[]()0.9262.600DRNet (ensemble)
[]()0.9262.600yw
Anatomy-XNet: An Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification in Chest X-rays0.9262.600Anatomy-XNet-V12021-06-10
[]()0.9252.400hoanganh_VB_ensemble3
[]()0.9252.400alimebkovk
[]()0.9242.600uest
[]()0.9242.400Hoang_VB_ensemble31_v
[]()0.9242.400tedtt
[]()0.9242.400as-hust-v3
[]()0.9242.400hoanganh_VB_VN
[]()0.9242.400Hierarchical-CNN-Ensemble-V1 (ensemble)
[]()0.9232.600DE_APR ensemble ltt
[]()0.9232.600DE_APR_N ensemble ltt
[]()0.9232.600Multi-Stage-Learning-CNN-V2 (ensemble)
[]()0.9232.600Weighted-CNN(ensemble)
[]()0.9232.400hoanganhcnu_ensemble27_v
[]()0.9232.400YJ&&YWW :https://github.com/inisis/chexper
[]()0.9232.400as-hust-v1
[]()0.9232.400Maxium (ensemble)
[]()0.9222.800as-hust-v2
[]()0.9222.400Average-CNN(ensemble)
[]()0.9222.400MaxAUC
[]()0.9212.600zjr(ensembel)
[]()0.9212.400SuperCNNv3
[]()0.9212.400hyc
[]()0.9212.400hoangnguyenkcv1
[]()0.9202.600{"submit_id": "0x3c7b0af1b5784c159daf259c58543aa3", "predict_id": "0x67b23473183f4f43afa3b37edbc5d7fe", "submitter_id": "0x30db016ad564455ba055eb7f7f4402ac"
[]()0.9202.400HOANG_VB_VN_2
[]()0.9192.600BDNB
[]()0.9192.600JF Coolver ensemble
[]()0.9192.400thang ensemble colo
[]()0.9192.400hoangnn9 ensemble VBV
[]()0.9192.400JF aboy ensemble_V1 JF HEALTHCARE https://github.com/deadpoppy/CheXpert-Challeng
[]()0.9192.200{"submit_id": "0x33aeb0f2525e482a886196c273bdf1ba", "predict_id": "0xff2f60907da8440d98ff17f0af749535", "submitter_id": "0x0b382a226d4548c9b441f19b1907fe0f"
[]()0.9192.200brian-baseline-v2
[]()0.9182.600DE_JUN4_RS_EN ensemble LTT
[]()0.9182.600Mehdi_You (ensemble)
Category-Wise Fine-Tuning for Image Multi-label Classification with Partial Labels✓ Link0.9182.600A Good Model (single model) Macao Polytechnic University2023-11-27
[]()0.9182.600A Good Model (single model)
Anatomy-XNet: An Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification in Chest X-rays0.9172.600Anatomy-XNet (ensemble)2021-06-10
[]()0.9172.400Ensemble_v2
[]()0.9172.200Deep-CNNs-V1
[]()0.9172.200vdn6 ensemble ltt
[]()0.9172.200Overfit ensemble OTH-A
[]()0.9172.000thangbk(ensemble)
[]()0.9162.600desmond
[]()0.9162.600DE_JUN1_RS_EN ensemble LTT
[]()0.9162.400DE_JUN3_RS_EN ensemble LTT
[]()0.9162.400{"submit_id": "0x57dc2989f0474ca095d0841df09cfb18", "predict_id": "0xd43bcf7d4c9b467894db2b274b18794e", "submitter_id": "0x30db016ad564455ba055eb7f7f4402ac"
[]()0.9162.400ATT-AW-v1
[]()0.9162.200{"submit_id": "0xeb9c9e79ed9e4410a2a37d62322f4585", "predict_id": "0x735b718280b14e83895decbc31641f87", "submitter_id": "0x30db016ad564455ba055eb7f7f4402ac"
[]()0.9162.200Multi-Stage-Learning-CNN-V0
[]()0.9152.600TGNB
[]()0.9152.400ensemble SN
[]()0.9152.400zhangjingyan
[]()0.9152.200Deadpoppy Ensemble
[]()0.9152.200hoangnguyenkcv-ensemble28
[]()0.9142.600DE_JUN2_RS_EN ensemble LTT
[]()0.9142.400GRNB
[]()0.9142.000Deep-CNNs (ensemble)
[]()0.9132.200Sky-Model
[]()0.9132.200JF Deadpoppy
[]()0.9132.000YWW-YJ:https://github.com/inisis/chexper
[]()0.9122.200zjy
[]()0.9122.000WL_Baseline (ensemble)
[]()0.9112.200KCV-CNN-ensemble-CN
[]()0.9112.200songta
[]()0.9112.200bhtrun
[]()0.9112.200anatomy_xnet_v1 (single model)
[]()0.9112.000DS_APR_N single model ltt
[]()0.9112.000DS_APR single model LTT
[]()0.9112.000brian-baseline
[]()0.9102.200ensemble SNU
[]()0.9092.200HinaNetV2 (ensemble)
[]()0.9092.000KD-Prune10 (Single model)
[]()0.9091.800G_Mans_ensembl
Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring0.909Masks and Manuscripts2024-07-23
[]()0.9082.000guran_ri
[]()0.9081.800vdnnn (ensemble)
[]()0.9081.800BAAZT
CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison✓ Link0.9071.800Stanford Baseline (ensemble)2019-01-21
[]()0.9071.600vbn (single model)
[]()0.9071.600muti_base (ensemble)
[]()0.9071.400Z_Ensemble_V
[]()0.9061.600{ForwardModelEnsembleCorrected} (ensemble)
[]()0.9061.600LBC-v2 (ensemble)
[]()0.9061.600LBC-v2
Image Projective Transformation Rectification with Synthetic Data for Smartphone-captured Chest X-ray Photos Classification✓ Link0.9061.600LBC-v2 (ensemble)2022-10-12
[]()0.9052.000Multi-CNN
[]()0.9051.800hy
[]()0.9051.600ForwardMECorrectedFull (ensemble)
[]()0.9041.200JustAnotherDensenet
[]()0.9031.600Orlando (single model)
[]()0.9022.000Max (single model)
[]()0.9021.800DeepLungsEnsemble
[]()0.9011.600Ensemble_v1
[]()0.9011.400Nakajima_ayas
[]()0.9001.600MLC11 NotDense (single-model)
[]()0.9001.200vn_2 single_model ltt
[]()0.8992.000{AVG_MAX}(ensemble)
[]()0.8991.800Z_Ensemble_
[]()0.8991.600llllldz
[]()0.8991.600DiseaseNet Samg2003 single model, UIUC, http://sambhavgupta.com
[]()0.8991.600DiseaseNet Samg2003 single model, DPS RKP, http://sambhavgupta.co
[]()0.8991.400LBC-v0
[]()0.8991.400LBC-v0 (ensemble)
Image Projective Transformation Rectification with Synthetic Data for Smartphone-captured Chest X-ray Photos Classification✓ Link0.8991.400LBC-v0 (ensemble)2022-10-12
[]()0.8981.800BUA
[]()0.8981.400G_Mans_v2 (single model): LibAUC + coat_mini
[]()0.8981.200ljc226
[]()0.8971.600ForwardModelEnsemble (ensemble)
[]()0.8971.600NewTrickTest (ensemble)
[]()0.8971.200AccidentNet v1 (single model)
[]()0.8961.600ylz-v01
[]()0.8961.400ldz
[]()0.8961.400Densenet
[]()0.8961.400Stellarium-CheXpert-Local (single model)
[]()0.8961.400Stellarium-CheXpert-Local
Image Projective Transformation Rectification with Synthetic Data for Smartphone-captured Chest X-ray Photos Classification✓ Link0.8961.400Stellarium-CheXpert-Local2022-10-12
[]()0.8951.800Deadpoppy Single
[]()0.8951.600adoudo
[]()0.8951.400{koala-large} (single model)
[]()0.8951.200MVD121
[]()0.8951.000hust(single model)
[]()0.8941.600MM1
[]()0.8941.600hycN
[]()0.8941.600zhujier
[]()0.8941.000U-Random-Ind (single)
[]()0.8921.600HybridModelEnsemble (ensemble)
[]()0.8911.200MVD121-320
[]()0.8911.000ylz-v02
[]()0.8901.000pause
[]()0.8901.000Overfit ensemble OT
[]()0.8900.800Haruka_Hamasak
[]()0.8891.400DenseNet169 at 320x320 (single model)
[]()0.8891.400LR-baseline (ensemble)
[]()0.8881.000DataAugFTW (single model)
[]()0.8881.000{koala} (single model)
[]()0.8871.200Xception (single model)
[]()0.8871.200Stellarium (single model)
[]()0.8871.200Stellarium
[]()0.8871.200pm_rn50_0.15pp
[]()0.8861.200baseline3
[]()0.8861.000PrateekMunja
[]()0.8860.800MVR50
[]()0.8841.600MNet-Fix (Single Model)
[]()0.8840.800Coolver XH
[]()0.8831.200Naive Densenet
[]()0.8830.600mhealth_buet (single model)
[]()0.8820.800Aoitori (single model)
[]()0.8820.600{chexpert-classifier}(single model)
[]()0.8820.400DearBrave (single model)
[]()0.8811.000AccidentNet V2 (single model)
[]()0.8801.200{densenet} (single model)
[]()0.8790.600Yoake (single model)
[]()0.8780.600MLC11 Baseline (single-model)
[]()0.8761.200DenseNet
[]()0.8761.000HCL1 (single model)
[]()0.8751.200MLGCN (single model)
[]()0.8751.000GCN_densenet121-single mode
[]()0.8730.800GreenTeaCalpis (single model)
[]()0.8730.400Multi-CNN (ensemble)
[]()0.8710.600BASELINE ResNet50
[]()0.8680.800baseline1 (single model)
[]()0.8680.600Baseline DenseNet161
[]()0.8650.600DSENet
[]()0.8630.800Densenet-Basic Single NUS
[]()0.8620.800KD_Mobilenet (single model)
[]()0.8611.000{GoDense} (single model)
[]()0.8610.400inceptionv3_single_NN
[]()0.8600.800MLKD (Single model)
[]()0.8600.600BASELINE Acorn
[]()0.8590.600ErrorNet (single model)
[]()0.8590.600SleepNet (single model)
[]()0.8581.000baseline2
[]()0.8580.000UMLS_CLIP (single model)
[]()0.8540.800haw02 (single model)
[]()0.8530.000CombinedTrainDenseNet121 (single model)
[]()0.8510.400rayOfLightSingle (Single Model)
[]()0.8500.600Model_Team_34 (single model)
[]()0.8500.400Test model habbe
[]()0.8480.600model2_DenseNet121
[]()0.8480.200Baseline
[]()0.8440.400HinaNet (single model)
[]()0.8420.200singlehead_models (single model combined)
[]()0.8400.400mwowra-conditional (single)
[]()0.8380.400multihead_model (one model for all pathologies)
[]()0.8370.200mobilenet (single model)
[]()0.8350.000Grp12BigCNN
[]()0.8340.400MLC9_Densenet (single model)
[]()0.8300.200Grp12v2USup2OSamp (ensemble)
[]()0.8220.000DNET121-single
CheXclusion: Fairness gaps in deep chest X-ray classifiers✓ Link0.805DensNet1212020-02-14
[]()0.7970.600G_Mans_v1 (single model):
[]()0.7690.00012ASLv2(single)
[]()0.7600.000DenseNet121 (single model)
[]()0.7360.00012ASLv1(single)
[]()0.7320.600haw-baseline (single model)
[]()0.7270.000rayOfLight (ensemble)
[]()0.7240.000BASELINE DenseNet121
[]()0.6180.200Chest-x-ray classification using
[]()0.6150.000BME_Final_v2
[]()0.6060.000{densenet121}{single model
[]()0.6060.000autobot
[]()0.5750.000{MLC02_DenseNet121}
[]()0.5310.000efficiantB5 (single model)
[]()0.5240.000apalepu1
[]()0.5000.000Erdem (single)
[]()0.4810.000Adalab Standard (Single Model)
[]()0.4810.000Adalab Standard (single model)
[]()0.4790.000zeroshot_medclip_baseline (ensemble)
Check out how to contribute new results.