</> Code with Papers by Syntology

Browse › Computer Vision › Multi-Label Classification › CheXpert

Multi-Label Classification archive 2025-07-28

CheXpert Benchmark (Multi-Label Classification)

226 rows 10 with code listed 2 metrics Dataset page

Multi-Label Classification is the supervised learning problem where an instance may be associated with multiple labels. This is an extension of single-label classification (i.e., multi-class, or binary) where each instance is only associated with a single class label.

Source: Deep Learning for Multi-label Classification

The archive carries no text for this table; the description above is the archive's text for the task Multi-Label Classification. archive 2025-07-28

Over time archive 2025-07-28

The chart needs JavaScript; the table below carries every value.

Direction inferred from the metric name, not from the archive: AVERAGE AUC ON 14 LABEL (higher is better). Not inferred (points only, no best-so-far line): NUM RADS BELOW CURVE. Points are placed at the row's paper date; 13 of 226 rows carry one.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 CFT (ensemble) Macao Polytechnic University 0.933 – Paper Code 2023 linked, not harvested report
2 DeepAUC-v1 0.9302.800 – Paper Code 2020 linked, not harvested report
3 Hierarchical-Learning-V1 (ensemble) 0.9302.600 – Paper Code 2019 linked, not harvested report
4 YWW(ensemble) 0.9292.800 – – – not matched report
5 Conditional-Training-LSR 0.9292.600 – – – not matched report
6 Hierarchical-Learning-V4 (ensemble) 0.9292.600 – Paper Code 2019 linked, not harvested report
7 Conditional-Training-LSR-V1 0.9292.600 – – – not matched report
8 Hierarchical-Learning-V0 (ensemble) 0.9292.600 – – – not matched report
9 Multi-Stage-Learning-CNN-V3 (ensemble) 0.9282.600 – – – not matched report
10 DeepCNNsGM(ensemble) 0.9282.600 – – – not matched report
11 inisis 0.9273.000 – – – not matched report
12 DeepCNNs(ensemble) 0.9272.600 – – – not matched report
13 SenseXDR 0.9272.600 – – – not matched report
14 ihil (ensemble) 0.9272.600 – – – not matched report
15 JF aboy ensemble_V2 JF HEALTHCARE https://github.com/deadpoppy/CheXpert-Challeng 0.9263.000 – – – not matched report
16 DRNet (ensemble) 0.9262.600 – – – not matched report
17 yw 0.9262.600 – – – not matched report
18 Anatomy-XNet-V1 0.9262.600 – Paper – 2021 no code linked report
19 hoanganh_VB_ensemble3 0.9252.400 – – – not matched report
20 alimebkovk 0.9252.400 – – – not matched report
21 uest 0.9242.600 – – – not matched report
22 Hoang_VB_ensemble31_v 0.9242.400 – – – not matched report
23 tedtt 0.9242.400 – – – not matched report
24 as-hust-v3 0.9242.400 – – – not matched report
25 hoanganh_VB_VN 0.9242.400 – – – not matched report
26 Hierarchical-CNN-Ensemble-V1 (ensemble) 0.9242.400 – – – not matched report
27 DE_APR ensemble ltt 0.9232.600 – – – not matched report
28 DE_APR_N ensemble ltt 0.9232.600 – – – not matched report
29 Multi-Stage-Learning-CNN-V2 (ensemble) 0.9232.600 – – – not matched report
30 Weighted-CNN(ensemble) 0.9232.600 – – – not matched report
31 hoanganhcnu_ensemble27_v 0.9232.400 – – – not matched report
32 YJ&&YWW :https://github.com/inisis/chexper 0.9232.400 – – – not matched report
33 as-hust-v1 0.9232.400 – – – not matched report
34 Maxium (ensemble) 0.9232.400 – – – not matched report
35 as-hust-v2 0.9222.800 – – – not matched report
36 Average-CNN(ensemble) 0.9222.400 – – – not matched report
37 MaxAUC 0.9222.400 – – – not matched report
38 zjr(ensembel) 0.9212.600 – – – not matched report
39 SuperCNNv3 0.9212.400 – – – not matched report
40 hyc 0.9212.400 – – – not matched report
41 hoangnguyenkcv1 0.9212.400 – – – not matched report
42 {"submit_id": "0x3c7b0af1b5784c159daf259c58543aa3", "predict_id": "0x67b23473183f4f43afa3b37edbc5d7fe", "submitter_id": "0x30db016ad564455ba055eb7f7f4402ac" 0.9202.600 – – – not matched report
43 HOANG_VB_VN_2 0.9202.400 – – – not matched report
44 BDNB 0.9192.600 – – – not matched report
45 JF Coolver ensemble 0.9192.600 – – – not matched report
46 thang ensemble colo 0.9192.400 – – – not matched report
47 hoangnn9 ensemble VBV 0.9192.400 – – – not matched report
48 JF aboy ensemble_V1 JF HEALTHCARE https://github.com/deadpoppy/CheXpert-Challeng 0.9192.400 – – – not matched report
49 {"submit_id": "0x33aeb0f2525e482a886196c273bdf1ba", "predict_id": "0xff2f60907da8440d98ff17f0af749535", "submitter_id": "0x0b382a226d4548c9b441f19b1907fe0f" 0.9192.200 – – – not matched report
50 brian-baseline-v2 0.9192.200 – – – not matched report
51 DE_JUN4_RS_EN ensemble LTT 0.9182.600 – – – not matched report
52 Mehdi_You (ensemble) 0.9182.600 – – – not matched report
53 A Good Model (single model) Macao Polytechnic University 0.9182.600 – Paper Code 2023 linked, not harvested report
54 A Good Model (single model) 0.9182.600 – – – not matched report
55 Anatomy-XNet (ensemble) 0.9172.600 – Paper – 2021 no code linked report
56 Ensemble_v2 0.9172.400 – – – not matched report
57 Deep-CNNs-V1 0.9172.200 – – – not matched report
58 vdn6 ensemble ltt 0.9172.200 – – – not matched report
59 Overfit ensemble OTH-A 0.9172.200 – – – not matched report
60 thangbk(ensemble) 0.9172.000 – – – not matched report
61 desmond 0.9162.600 – – – not matched report
62 DE_JUN1_RS_EN ensemble LTT 0.9162.600 – – – not matched report
63 DE_JUN3_RS_EN ensemble LTT 0.9162.400 – – – not matched report
64 {"submit_id": "0x57dc2989f0474ca095d0841df09cfb18", "predict_id": "0xd43bcf7d4c9b467894db2b274b18794e", "submitter_id": "0x30db016ad564455ba055eb7f7f4402ac" 0.9162.400 – – – not matched report
65 ATT-AW-v1 0.9162.400 – – – not matched report
66 {"submit_id": "0xeb9c9e79ed9e4410a2a37d62322f4585", "predict_id": "0x735b718280b14e83895decbc31641f87", "submitter_id": "0x30db016ad564455ba055eb7f7f4402ac" 0.9162.200 – – – not matched report
67 Multi-Stage-Learning-CNN-V0 0.9162.200 – – – not matched report
68 TGNB 0.9152.600 – – – not matched report
69 ensemble SN 0.9152.400 – – – not matched report
70 zhangjingyan 0.9152.400 – – – not matched report
71 Deadpoppy Ensemble 0.9152.200 – – – not matched report
72 hoangnguyenkcv-ensemble28 0.9152.200 – – – not matched report
73 DE_JUN2_RS_EN ensemble LTT 0.9142.600 – – – not matched report
74 GRNB 0.9142.400 – – – not matched report
75 Deep-CNNs (ensemble) 0.9142.000 – – – not matched report
76 Sky-Model 0.9132.200 – – – not matched report
77 JF Deadpoppy 0.9132.200 – – – not matched report
78 YWW-YJ:https://github.com/inisis/chexper 0.9132.000 – – – not matched report
79 zjy 0.9122.200 – – – not matched report
80 WL_Baseline (ensemble) 0.9122.000 – – – not matched report
81 KCV-CNN-ensemble-CN 0.9112.200 – – – not matched report
82 songta 0.9112.200 – – – not matched report
83 bhtrun 0.9112.200 – – – not matched report
84 anatomy_xnet_v1 (single model) 0.9112.200 – – – not matched report
85 DS_APR_N single model ltt 0.9112.000 – – – not matched report
86 DS_APR single model LTT 0.9112.000 – – – not matched report
87 brian-baseline 0.9112.000 – – – not matched report
88 ensemble SNU 0.9102.200 – – – not matched report
89 HinaNetV2 (ensemble) 0.9092.200 – – – not matched report
90 KD-Prune10 (Single model) 0.9092.000 – – – not matched report
91 G_Mans_ensembl 0.9091.800 – – – not matched report
92 Masks and Manuscripts 0.909 – Paper – 2024 no code linked report
93 guran_ri 0.9082.000 – – – not matched report
94 vdnnn (ensemble) 0.9081.800 – – – not matched report
95 BAAZT 0.9081.800 – – – not matched report
96 Stanford Baseline (ensemble) 0.9071.800 – Paper Code 2019 0 of 1 ran · 1 unverified report
97 vbn (single model) 0.9071.600 – – – not matched report
98 muti_base (ensemble) 0.9071.600 – – – not matched report
99 Z_Ensemble_V 0.9071.400 – – – not matched report
100 {ForwardModelEnsembleCorrected} (ensemble) 0.9061.600 – – – not matched report
101 LBC-v2 (ensemble) 0.9061.600 – – – not matched report
102 LBC-v2 0.9061.600 – – – not matched report
103 LBC-v2 (ensemble) 0.9061.600 – Paper Code 2022 linked, not harvested report
104 Multi-CNN 0.9052.000 – – – not matched report
105 hy 0.9051.800 – – – not matched report
106 ForwardMECorrectedFull (ensemble) 0.9051.600 – – – not matched report
107 JustAnotherDensenet 0.9041.200 – – – not matched report
108 Orlando (single model) 0.9031.600 – – – not matched report
109 Max (single model) 0.9022.000 – – – not matched report
110 DeepLungsEnsemble 0.9021.800 – – – not matched report
111 Ensemble_v1 0.9011.600 – – – not matched report
112 Nakajima_ayas 0.9011.400 – – – not matched report
113 MLC11 NotDense (single-model) 0.9001.600 – – – not matched report
114 vn_2 single_model ltt 0.9001.200 – – – not matched report
115 {AVG_MAX}(ensemble) 0.8992.000 – – – not matched report
116 Z_Ensemble_ 0.8991.800 – – – not matched report
117 llllldz 0.8991.600 – – – not matched report
118 DiseaseNet Samg2003 single model, UIUC, http://sambhavgupta.com 0.8991.600 – – – not matched report
119 DiseaseNet Samg2003 single model, DPS RKP, http://sambhavgupta.co 0.8991.600 – – – not matched report
120 LBC-v0 0.8991.400 – – – not matched report
121 LBC-v0 (ensemble) 0.8991.400 – – – not matched report
122 LBC-v0 (ensemble) 0.8991.400 – Paper Code 2022 linked, not harvested report
123 BUA 0.8981.800 – – – not matched report
124 G_Mans_v2 (single model): LibAUC + coat_mini 0.8981.400 – – – not matched report
125 ljc226 0.8981.200 – – – not matched report
126 ForwardModelEnsemble (ensemble) 0.8971.600 – – – not matched report
127 NewTrickTest (ensemble) 0.8971.600 – – – not matched report
128 AccidentNet v1 (single model) 0.8971.200 – – – not matched report
129 ylz-v01 0.8961.600 – – – not matched report
130 ldz 0.8961.400 – – – not matched report
131 Densenet 0.8961.400 – – – not matched report
132 Stellarium-CheXpert-Local (single model) 0.8961.400 – – – not matched report
133 Stellarium-CheXpert-Local 0.8961.400 – – – not matched report
134 Stellarium-CheXpert-Local 0.8961.400 – Paper Code 2022 linked, not harvested report
135 Deadpoppy Single 0.8951.800 – – – not matched report
136 adoudo 0.8951.600 – – – not matched report
137 {koala-large} (single model) 0.8951.400 – – – not matched report
138 MVD121 0.8951.200 – – – not matched report
139 hust(single model) 0.8951.000 – – – not matched report
140 MM1 0.8941.600 – – – not matched report
141 hycN 0.8941.600 – – – not matched report
142 zhujier 0.8941.600 – – – not matched report
143 U-Random-Ind (single) 0.8941.000 – – – not matched report
144 HybridModelEnsemble (ensemble) 0.8921.600 – – – not matched report
145 MVD121-320 0.8911.200 – – – not matched report
146 ylz-v02 0.8911.000 – – – not matched report
147 pause 0.8901.000 – – – not matched report
148 Overfit ensemble OT 0.8901.000 – – – not matched report
149 Haruka_Hamasak 0.8900.800 – – – not matched report
150 DenseNet169 at 320x320 (single model) 0.8891.400 – – – not matched report
151 LR-baseline (ensemble) 0.8891.400 – – – not matched report
152 DataAugFTW (single model) 0.8881.000 – – – not matched report
153 {koala} (single model) 0.8881.000 – – – not matched report
154 Xception (single model) 0.8871.200 – – – not matched report
155 Stellarium (single model) 0.8871.200 – – – not matched report
156 Stellarium 0.8871.200 – – – not matched report
157 pm_rn50_0.15pp 0.8871.200 – – – not matched report
158 baseline3 0.8861.200 – – – not matched report
159 PrateekMunja 0.8861.000 – – – not matched report
160 MVR50 0.8860.800 – – – not matched report
161 MNet-Fix (Single Model) 0.8841.600 – – – not matched report
162 Coolver XH 0.8840.800 – – – not matched report
163 Naive Densenet 0.8831.200 – – – not matched report
164 mhealth_buet (single model) 0.8830.600 – – – not matched report
165 Aoitori (single model) 0.8820.800 – – – not matched report
166 {chexpert-classifier}(single model) 0.8820.600 – – – not matched report
167 DearBrave (single model) 0.8820.400 – – – not matched report
168 AccidentNet V2 (single model) 0.8811.000 – – – not matched report
169 {densenet} (single model) 0.8801.200 – – – not matched report
170 Yoake (single model) 0.8790.600 – – – not matched report
171 MLC11 Baseline (single-model) 0.8780.600 – – – not matched report
172 DenseNet 0.8761.200 – – – not matched report
173 HCL1 (single model) 0.8761.000 – – – not matched report
174 MLGCN (single model) 0.8751.200 – – – not matched report
175 GCN_densenet121-single mode 0.8751.000 – – – not matched report
176 GreenTeaCalpis (single model) 0.8730.800 – – – not matched report
177 Multi-CNN (ensemble) 0.8730.400 – – – not matched report
178 BASELINE ResNet50 0.8710.600 – – – not matched report
179 baseline1 (single model) 0.8680.800 – – – not matched report
180 Baseline DenseNet161 0.8680.600 – – – not matched report
181 DSENet 0.8650.600 – – – not matched report
182 Densenet-Basic Single NUS 0.8630.800 – – – not matched report
183 KD_Mobilenet (single model) 0.8620.800 – – – not matched report
184 {GoDense} (single model) 0.8611.000 – – – not matched report
185 inceptionv3_single_NN 0.8610.400 – – – not matched report
186 MLKD (Single model) 0.8600.800 – – – not matched report
187 BASELINE Acorn 0.8600.600 – – – not matched report
188 ErrorNet (single model) 0.8590.600 – – – not matched report
189 SleepNet (single model) 0.8590.600 – – – not matched report
190 baseline2 0.8581.000 – – – not matched report
191 UMLS_CLIP (single model) 0.8580.000 – – – not matched report
192 haw02 (single model) 0.8540.800 – – – not matched report
193 CombinedTrainDenseNet121 (single model) 0.8530.000 – – – not matched report
194 rayOfLightSingle (Single Model) 0.8510.400 – – – not matched report
195 Model_Team_34 (single model) 0.8500.600 – – – not matched report
196 Test model habbe 0.8500.400 – – – not matched report
197 model2_DenseNet121 0.8480.600 – – – not matched report
198 Baseline 0.8480.200 – – – not matched report
199 HinaNet (single model) 0.8440.400 – – – not matched report
200 singlehead_models (single model combined) 0.8420.200 – – – not matched report
201 mwowra-conditional (single) 0.8400.400 – – – not matched report
202 multihead_model (one model for all pathologies) 0.8380.400 – – – not matched report
203 mobilenet (single model) 0.8370.200 – – – not matched report
204 Grp12BigCNN 0.8350.000 – – – not matched report
205 MLC9_Densenet (single model) 0.8340.400 – – – not matched report
206 Grp12v2USup2OSamp (ensemble) 0.8300.200 – – – not matched report
207 DNET121-single 0.8220.000 – – – not matched report
208 DensNet121 0.805 – Paper Code 2020 linked, not harvested report
209 G_Mans_v1 (single model): 0.7970.600 – – – not matched report
210 12ASLv2(single) 0.7690.000 – – – not matched report
211 DenseNet121 (single model) 0.7600.000 – – – not matched report
212 12ASLv1(single) 0.7360.000 – – – not matched report
213 haw-baseline (single model) 0.7320.600 – – – not matched report
214 rayOfLight (ensemble) 0.7270.000 – – – not matched report
215 BASELINE DenseNet121 0.7240.000 – – – not matched report
216 Chest-x-ray classification using 0.6180.200 – – – not matched report
217 BME_Final_v2 0.6150.000 – – – not matched report
218 {densenet121}{single model 0.6060.000 – – – not matched report
219 autobot 0.6060.000 – – – not matched report
220 {MLC02_DenseNet121} 0.5750.000 – – – not matched report
221 efficiantB5 (single model) 0.5310.000 – – – not matched report
222 apalepu1 0.5240.000 – – – not matched report
223 Erdem (single) 0.5000.000 – – – not matched report
224 Adalab Standard (Single Model) 0.4810.000 – – – not matched report
225 Adalab Standard (single model) 0.4810.000 – – – not matched report
226 zeroshot_medclip_baseline (ensemble) 0.4790.000 – – – not matched report

All 226 rows shown. 13 link to a paper page on this site; 0 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 1 rows have a graph line, from 1 distinct papers; 0 rows (0 papers) have at least one sample that ran. Counting each paper once: Syntology ran 0 of 1 samples; 1 unverified. Separately, 1 of those 1 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections