HyperAI초신경

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

한국어

HyperAI초신경

Overlapped 15 1 On Pascal Voc 2012

평가 지표

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	mIoU	Paper Title	Repository
SDR	39.5	Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations	-
MBS	80.6	Mitigating Background Shift in Class-Incremental Semantic Segmentation
MiB	29.29	PLOP: Learning without Forgetting for Continual Semantic Segmentation
ILT	9.2	Incremental Learning Techniques for Semantic Segmentation
SSUL-M	71.37	SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
SATS-M	76.61	SATS: Self-Attention Transfer for Continual Semantic Segmentation
PLOP	54.64	PLOP: Learning without Forgetting for Continual Semantic Segmentation
SATS	74.48	SATS: Self-Attention Transfer for Continual Semantic Segmentation
PLOPLong	61.21	Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
LWF	5.5	Learning without Forgetting
SSUL	67.61	SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
RCNet-101	59.4	Representation Compensation Networks for Continual Semantic Segmentation
SSUL+AWT	67.6	Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation

0 of 13 row(s) selected.