Overlapped 100 5 On Ade20K

Metrics

mIoU

Results

Performance results of various models on this benchmark

		Paper Title
MBS	42.8	Mitigating Background Shift in Class-Incremental Semantic Segmentation
SSUL-M	34.56	SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
SSUL	32.48	SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
MiB+AWT	31.1	Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation
RCNet-101	29.6	Representation Compensation Networks for Continual Semantic Segmentation
PLOP	28.75	PLOP: Learning without Forgetting for Continual Semantic Segmentation
MiB	25.96	PLOP: Learning without Forgetting for Continual Semantic Segmentation
ILT	0.5	Incremental Learning Techniques for Semantic Segmentation

0 of 8 row(s) selected.