Multi-task Learning (Segmentation, Depth, Surface Normal) on NYU v2 (test) benchmark leaderboard · SOTA2 Research

Multi-task Learning (Segmentation, Depth, Surface Normal) on NYU v2 (test)

40.42mIoUGO4Align

Evaluation Results

Method	Links
GO4Align2024.04		40.42	65.37	0.5492	0.2167	24.76	18.94	30.54	57.87	69.84	2.11	-6.08
NASHMTL2024.04		40.13	65.93	0.5261	0.2171	25.26	20.08	28.4	55.47	68.15	2.89	-4.04
CAGRAD2024.04		39.79	65.49	0.5486	0.225	26.31	21.58	25.61	52.36	65.58	5.33	0.2
GRADDROP2024.04		39.39	65.12	0.5455	0.2279	27.48	22.96	23.38	49.44	62.87	7.89	3.58
IMTL-G2024.04		39.35	65.6	0.5426	0.2256	26.02	21.19	26.2	53.13	66.24	4.56	-0.76
LS2024.04		39.29	65.33	0.5493	0.2263	28.15	23.96	22.09	47.5	61.08	9.89	5.59
DWA2024.04		39.11	65.31	0.551	0.2285	27.61	23.18	24.17	50.18	62.39	8.67	3.57
FAMO2024.04		38.88	64.9	0.5474	0.2194	25.06	19.57	29.21	56.61	68.98	4.33	-4.1
SI2024.04		38.45	64.27	0.5354	0.2201	27.6	23.37	22.53	48.57	62.32	8.78	4.39
STL2024.04		38.3	63.76	0.6754	0.278	25.01	19.21	30.14	57.2	69.15	—	—
PCGRAD2024.04		38.06	64.64	0.555	0.2325	27.41	22.8	23.86	49.83	63.14	9	3.97
RLW2024.04		37.17	63.77	0.5759	0.241	28.27	24.18	22.26	47.05	60.62	12.22	7.78
UW2024.04		36.87	63.17	0.5446	0.226	27.04	22.61	23.54	49.05	63.65	8.33	4.05
MGDA2024.04		30.47	59.9	0.607	0.2555	24.88	19.45	29.18	56.88	69.36	7	1.38