Share your thoughts, 1 month free Claude Pro on usSee more

Object Hallucination Mitigation on AMBER

12.1CHAIR

ICD

Updated 1mo ago

Evaluation Results

Method	Links
ICD 2026.04		12.1	52.6	51.4	5.2
Baseline 2026.04		11.6	53.4	51.7	5.3
Baseline 2026.04		11.5	50.1	48.9	4.6
M3ID 2026.04		11.5	52.5	51.4	4.6
VAF 2026.04		10.9	33	28.1	3.7
Vanilla 2026.04		10.6	50.9	36.4	4.1
Vanilla 2026.04		10.6	50.9	36.4	4.1
VCD 2026.04		10.2	53.5	46.9	4.8
VCD 2026.04		9.9	51.2	43.4	4.6
M3ID 2026.04		9.8	55.6	48.4	3.6
ICD 2026.04		9.3	50.5	41.3	4.9
ICD 2026.04		9.1	51.2	40.6	4.3
FLB 2026.04		9	53.6	43.8	4.7
VCD 2026.04		8.9	51.8	41.9	4.3
MoD 2026.04		8.6	50.7	38.8	4.7
LLaVA-1.5-7B (Base) 2026.04		7.8	51	36.4	4.2
STIC 2026.04		7.6	52.1	35.8	4.4
Nullu 2026.04		7.4	48.2	30.5	3.7
Nullu 2026.04		7.4	48.2	30.5	3.7
ICT 2026.04		7	48	28.4	3.5
VTI 2026.04		6.7	47.6	28.1	3.6
VTI 2026.04		6.7	47.6	28.1	3.6
VCD 2026.04		6.7	46.5	27.8	2
MESA 2026.04		6.4	50.4	27.4	3.2
MESA 2026.04		6.4	50.4	27.4	3.2
AVISC 2026.04		6.3	46.6	25.6	2
FLB 2026.04		6.1	50.4	31.6	2.7
M3ID 2026.04		6	48.9	26	1.5
EOS 2026.04		5.1	49.1	22.7	2
SENA 2026.04		4.9	49.4	20.5	1.7
Octopus 2026.04		4.8	49.2	23.4	1.2
GPT-4V 2026.04		4.6	67.1	30.7	2.6
MRGD 2026.04		4.4	62.5	21.9	-
PSRD 2026.04		3.9	48.2	20.1	2
CLIP-DPO 2026.04		3.7	47.8	16.6	1.3
RLAIF-V 2026.04		2.9	50.2	16	1
LLaVA-DPO 2026.04		2.8	47.8	15.5	1.6
HSA-DPO 2026.04		2.1	47.3	13.4	1.2