Multi Label Classification On Chexpert

Metrics

AVERAGE AUC ON 14 LABEL

NUM RADS BELOW CURVE

Results

Performance results of various models on this benchmark

Comparison Table

Model Name	AVERAGE AUC ON 14 LABEL	NUM RADS BELOW CURVE
Model 1	0.903	1.600
Model 2	0.879	0.600
Model 3	0.911	2.200
Model 4	0.882	0.600
Model 5	0.618	0.200
Model 6	0.899	1.600
Model 7	0.923	2.400
Model 8	0.897	1.200
Model 9	0.919	2.200
Model 10	0.917	2.400
Model 11	0.909	2.200
Model 12	0.881	1.000
Model 13	0.912	2.000
Model 14	0.884	0.800
Model 15	0.909	2.000
Model 16	0.927	2.600
Model 17	0.850	0.600
Model 18	0.923	2.400
Model 19	0.862	0.800
Model 20	0.924	2.400
Model 21	0.923	2.600
Model 22	0.899	1.400
Model 23	0.922	2.800
Model 24	0.929	2.800
Model 25	0.887	1.200
Model 26	0.915	2.200
Model 27	0.913	2.200
Model 28	0.860	0.600
Model 29	0.887	1.200
Model 30	0.887	1.200
Model 31	0.889	1.400
Model 32	0.906	1.600
Model 33	0.913	2.000
Model 34	0.908	2.000
Model 35	0.897	1.600
Model 36	0.865	0.600
Model 37	0.923	2.400
projective-transformation-rectification-for	0.906	1.600
Model 39	0.915	2.200
Model 40	0.916	2.400
Model 41	0.889	1.400
Model 42	0.900	1.200
category-wise-fine-tuning-for-image-multi	0.933	-
Model 44	0.838	0.400
Model 45	0.834	0.400
Model 46	0.895	1.000
Model 47	0.901	1.400
Model 48	0.919	2.600
Model 49	0.760	0.000
Model 50	0.886	0.800
Model 51	0.929	2.600
Model 52	0.913	2.200
Model 53	0.481	0.000
Model 54	0.899	1.400
Model 55	0.929	2.600
Model 56	0.914	2.000
Model 57	0.919	2.400
Model 58	0.884	1.600
Model 59	0.925	2.400
Model 60	0.928	2.600
Model 61	0.898	1.800
Model 62	0.924	2.400
Model 63	0.924	2.400
Model 64	0.917	2.200
Model 65	0.844	0.400
Model 66	0.916	2.200
Model 67	0.909	1.800
Model 68	0.920	2.600
Model 69	0.927	2.600
Model 70	0.927	3.000
Model 71	0.863	0.800
Model 72	0.848	0.200
Model 73	0.899	1.600
Model 74	0.917	2.200
Model 75	0.906	1.600
Model 76	0.875	1.200
Model 77	0.769	0.000
Model 78	0.899	2.000
Model 79	0.905	1.600
Model 80	0.887	1.200
Model 81	0.880	1.200
Model 82	0.878	0.600
Model 83	0.923	2.400
Model 84	0.876	1.200
Model 85	0.732	0.600
Model 86	0.902	2.000
Model 87	0.923	2.600
Model 88	0.916	2.400
Model 89	0.886	1.000
Model 90	0.882	0.800
Model 91	0.911	2.000
Model 92	0.724	0.000
Model 93	0.919	2.600
anatomy-x-net-a-semi-supervised-anatomy-aware	0.917	2.600
Model 95	0.916	2.600
interpreting-chest-x-rays-via-cnns-that	0.929	2.600
Model 97	0.898	1.200
Model 98	0.907	1.600
Model 99	0.904	1.200
Model 100	0.925	2.400
Model 101	0.926	2.600
Model 102	0.500	0.000
Model 103	0.918	2.600
Model 104	0.914	2.600
Model 105	0.894	1.600
Model 106	0.890	1.000
projective-transformation-rectification-for	0.899	1.400
Model 108	0.860	0.800
robust-deep-auc-maximization-a-new-surrogate	0.930	2.800
Model 110	0.922	2.400
Model 111	0.918	2.600
Model 112	0.883	1.200
Model 113	0.524	0.000
Model 114	0.928	2.600
Model 115	0.876	1.000
category-wise-fine-tuning-for-image-multi	0.918	2.600
Model 117	0.918	2.600
Model 118	0.914	2.400
Model 119	0.920	2.400
Model 120	0.921	2.400
Model 121	0.897	1.600
interpreting-chest-x-rays-via-cnns-that	0.930	2.600
Model 123	0.919	2.400
Model 124	0.895	1.800
Model 125	0.921	2.400
Model 126	0.907	1.600
Model 127	0.797	0.600
Model 128	0.894	1.600
Model 129	0.896	1.400
Model 130	0.894	1.600
Model 131	0.853	0.000
Model 132	0.923	2.600
Model 133	0.924	2.400
Model 134	0.895	1.400
Model 135	0.888	1.000
Model 136	0.908	1.800
Model 137	0.911	2.200
Model 138	0.859	0.600
Model 139	0.840	0.400
anatomy-x-net-a-semi-supervised-anatomy-aware	0.926	2.600
Model 141	0.898	1.400
Model 142	0.875	1.000
masks-and-manuscripts-advancing-medical-pre	0.909	-
Model 144	0.891	1.000
Model 145	0.859	0.600
Model 146	0.822	0.000
Model 147	0.882	0.400
Model 148	0.916	2.200
Model 149	0.868	0.600
Model 150	0.917	2.000
Model 151	0.861	0.400
Model 152	0.911	2.000
Model 153	0.892	1.600
Model 154	0.895	1.200
chexclusion-fairness-gaps-in-deep-chest-x-ray	0.805	-
Model 156	0.896	1.400
Model 157	0.873	0.800
Model 158	0.911	2.200
Model 159	0.896	1.400
Model 160	0.929	2.600
Model 161	0.727	0.000
Model 162	0.915	2.400
Model 163	0.924	2.400
Model 164	0.927	2.600
Model 165	0.899	1.800
Model 166	0.888	1.000
Model 167	0.910	2.200
Model 168	0.901	1.600
Model 169	0.917	2.200
Model 170	0.908	1.800
Model 171	0.868	0.800
Model 172	0.606	0.000
Model 173	0.830	0.200
Model 174	0.900	1.600
Model 175	0.923	2.600
Model 176	0.915	2.600
Model 177	0.606	0.000
Model 178	0.912	2.200
Model 179	0.911	2.000
Model 180	0.899	1.600
Model 181	0.921	2.600
Model 182	0.926	3.000
Model 183	0.615	0.000
Model 184	0.915	2.400
projective-transformation-rectification-for	0.896	1.400
Model 186	0.919	2.200
Model 187	0.479	0.000
Model 188	0.858	0.000
Model 189	0.481	0.000
Model 190	0.894	1.000
Model 191	0.871	0.600
Model 192	0.895	1.600
Model 193	0.919	2.400
Model 194	0.854	0.800
Model 195	0.907	1.400
Model 196	0.916	2.600
Model 197	0.905	2.000
Model 198	0.890	1.000
Model 199	0.575	0.000
Model 200	0.905	1.800
Model 201	0.890	0.800
Model 202	0.851	0.400
Model 203	0.842	0.200
Model 204	0.858	1.000
Model 205	0.835	0.000
Model 206	0.848	0.600
Model 207	0.896	1.400
Model 208	0.902	1.800
Model 209	0.922	2.400
Model 210	0.883	0.600
Model 211	0.921	2.400
chexpert-a-large-chest-radiograph-dataset	0.907	1.800
Model 213	0.891	1.200
Model 214	0.906	1.600
Model 215	0.837	0.200
Model 216	0.736	0.000
Model 217	0.850	0.400
Model 218	0.916	2.400
Model 219	0.861	1.000
Model 220	0.911	2.200
Model 221	0.873	0.400
Model 222	0.886	1.200
Model 223	0.531	0.000
Model 224	0.926	2.600
Model 225	0.896	1.600
Model 226	0.924	2.600