3D Object Detection on ONCE 500K unlabeled Samples (Medium) benchmark leaderboard · SOTA2 Research

3D Object Detection on ONCE 500K unlabeled Samples (Medium)

79.51Vehicle AP (Overall)PTPM + GeoTeacher

Evaluation Results

Method
PTPM + GeoTeacher2025.12	79.51	89.77	74.11	59.12	48.33	54.91	41.19	25.83	64.76	76.57	58.57	40.64	64.2
ProficientTeacher + GeoTeacher2025.12	78.94	87.34	73.41	60.7	42	48.11	35.55	21.77	63.94	73.93	58.71	43.38	61.62
ProficientTeacher2025.12	78.07	87.43	72.5	59.51	38.38	42.45	34.62	25.58	63.23	74.7	58.19	40.73	59.89
NoiseDet2025.12	77.14	87.21	69.94	58.44	40.45	44.91	35.71	24.11	62.59	73.04	57.98	42.67	60.06
PTPM2025.12	76.66	86.75	71.3	56.87	45.87	54.98	37.35	20.89	61.88	74.08	56.52	33.3	61.47
3DIoUMatch2025.12	75.69	86.46	70.22	56.06	34.14	38.84	29.19	19.62	58.93	69.08	54.16	38.87	56.25
Noisy Student2025.12	75.53	86.52	69.78	55.05	31.56	35.8	26.24	21.21	58.93	69.61	53.73	36.94	55.34
SESS2025.12	72.11	84.06	66.44	53.61	33.44	38.58	28.1	18.67	61.82	73.2	56.6	38.73	55.79