Anomaly Detection On Road Anomaly

Metrics

AP

FPR95

Results

Performance results of various models on this benchmark

			Paper Title
OodDINO	95.21	2.11	-
RbA	90.28	4.92	RbA: Segmenting Unknown Regions Rejected by All
DOoD	89.1	8.8	Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond
cDNP	85.6	9.8	Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection
Mask2Anomaly	79.70	13.45	Unmasking Anomalies in Road-Scene Segmentation
RPL+CoroCL	71.61	17.74	Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
PEBAL	45.10	44.58	Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes
Synboost	41.83	59.72	Pixel-wise Anomaly Detection in Complex Driving Scenes
SML	25.82	49.74	Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation
SynthCP	24.86	64.69	Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation

0 of 10 row(s) selected.

Anomaly Detection On Road Anomaly

Metrics

AP

FPR95

Results

Performance results of various models on this benchmark

			Paper Title
OodDINO	95.21	2.11	-
RbA	90.28	4.92	RbA: Segmenting Unknown Regions Rejected by All
DOoD	89.1	8.8	Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond
cDNP	85.6	9.8	Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection
Mask2Anomaly	79.70	13.45	Unmasking Anomalies in Road-Scene Segmentation
RPL+CoroCL	71.61	17.74	Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
PEBAL	45.10	44.58	Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes
Synboost	41.83	59.72	Pixel-wise Anomaly Detection in Complex Driving Scenes
SML	25.82	49.74	Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation
SynthCP	24.86	64.69	Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation

0 of 10 row(s) selected.