HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Overlapped 10 1 On Pascal Voc 2012

평가 지표

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	mIoU	Paper Title	Repository
LWF	4.8	Learning without Forgetting	-
MBS	77.19	Mitigating Background Shift in Class-Incremental Semantic Segmentation	-
SSUL	59.25	SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning	-
SATS-M	69.27	SATS: Self-Attention Transfer for Continual Semantic Segmentation	-
SDR	25.1	Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations	-
ILT	5.5	Incremental Learning Techniques for Semantic Segmentation	-
RCNet-101	34.3	Representation Compensation Networks for Continual Semantic Segmentation	-
PLOPLong	40.83	Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation	-
SATS	61.6	SATS: Self-Attention Transfer for Continual Semantic Segmentation	-
PLOP	30.45	PLOP: Learning without Forgetting for Continual Semantic Segmentation	-
MiB	20.1	Modeling the Background for Incremental Learning in Semantic Segmentation	-
SSUL+AWT	60.7	Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation	-
SSUL-M	64.12	SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning	-

0 of 13 row(s) selected.

Overlapped 10 1 On Pascal Voc 2012 | SOTA | HyperAI초신경