List your company

Failure Detection on Close Box Out-of-Distribution

100TPRTemporal Non-Distr. Min.
25.1244.566483.44Mar 12, 2026

Evaluation results

MethodLinks
Temporal Non-Distr. Min.Failure Detector Category=Diffusion2026.031002712.35
DDPM Loss (Eq. A.1)Failure Detector Category=Diffusion2026.031009414.54
Temporal DDPM LossFailure Detector Category=Diffusion2026.031003713.66
Policy EncoderFailure Detector Category=Embed.2026.0310001.59
CLIP PretrainedFailure Detector Category=Embed.2026.0310008.2
ResNet PretrainedFailure Detector Category=Embed.2026.03100015.51
GPT-4o Image QAFailure Detector Category=VLM2026.03100023.2
Gemini 1.5 Pro Image QAFailure Detector Category=VLM2026.03100023.2
Gemini 1.5 Pro Video QAFailure Detector Category=VLM2026.031005020.2
SentinelFailure Detector Category=Combined, Configuration=STAC MMD* + GPT-4o Video QA*2026.031009014.25
STAC For. KLFailure Detector Category=STAC2026.03998514.04
STAC MMD*Failure Detector Category=STAC2026.03999314.72
STAC Rev. KLFailure Detector Category=STAC2026.03939715.12
Temporal Diffusion Recon.Failure Detector Category=Diffusion2026.039210015.75
GPT-4o Video QA*Failure Detector Category=VLM2026.03699521.02
Claude 3.5 Sonnet Image QAFailure Detector Category=VLM2026.03691023.2
Claude 3.5 Sonnet Video QAFailure Detector Category=VLM2026.03444023.2
Diffusion Recon.Failure Detector Category=Diffusion2026.034010017.08
Diffusion Output VarianceFailure Detector Category=Diffusion2026.032810017.27