Fine-grained Open-vocabulary Object Detection on FG-OVD 1.0 (test) benchmark leaderboard · SOTA2 Research

Fine-grained Open-vocabulary Object Detection on FG-OVD 1.0 (test)

57.5Score (Hard)LaMI-DETR + GUIDED

Evaluation Results

Method	Links
LaMI-DETR + GUIDED2026.03		57.5	69.5	73.3	72.6	64.8	68.5	62	63.4	66.4
OWL-ViT + GUIDED2026.03		46.8	59.4	64.1	66.2	60.4	58.9	44.7	54.5	56.9
LaMI-DETR + Finetune2026.03		39.5	50.7	54.2	66	51.9	53.7	42.1	49.1	50.9
Grounding DINO + GUIDED2026.03		35.1	49.3	52.8	57.1	49.7	57	26.4	39.6	45.9
LaMI-DETR + HA-FGOVD*2026.03		33.5	45.9	47.5	63.8	52.7	42.6	36.9	50.1	46.6
OWL-ViT + HA-FGOVD2026.03		31.4	46	50.7	67.2	48.4	48.5	38	32.7	45.4
LaMI-DETR2026.03		29.2	40.6	42.9	63.5	49.5	39.2	34.6	46.2	43.2
OWL-ViT2026.03		26.6	39.8	44.5	67	44	45	36.2	29.2	41.5
OWL-ViT2026.03		26.2	39.8	38.4	53.9	45.3	37.3	26.6	34.1	37.7
OWLv22026.03		25.4	41.2	42.8	63.2	53.3	36.9	23.3	12.2	37.3
OWLv22026.03		25.3	38.5	40	52.9	45.1	33.5	19.2	28.5	35.4
ViLD2026.03		22.1	36.1	39.9	56.6	43.2	34.9	24.5	30.1	35.9
Grounding DINO + HA-FGOVD2026.03		19.2	32.3	34	62.2	41.5	33	32.1	29.2	35.4
OV-DINO2026.03		18.6	28.4	25	54.3	35.6	30	21	24.2	29.6
Grounding DINO2026.03		17	28.4	31	62.5	41.4	30.3	31	26.2	33.5
CORA2026.03		13.8	20	20.4	35.1	25	19.3	22	27.9	22.9
Detic2026.03		11.5	18.6	18.6	69.7	21.5	38.8	30.1	24.6	29.3