HyperAI초신경

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

한국어

HyperAI초신경

Continual Learning On Cifar100 20 Tasks

평가 지표

Average Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Average Accuracy	Paper Title	Repository
ALTA	92.98	Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation
CPG-light	77.0	EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING
Model Zoo-Continual	94.99	Model Zoo: A Growing "Brain" That Learns Continually
PAENet	77.1	Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning
CPG	80.9	Compacting, Picking and Growing for Unforgetting Continual Learning
kNN-CLIP	90.8	Revisiting a kNN-based Image Classification System with High-capacity Storage	-
PackNet	67.5	PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
CondConvContinual	77.4	EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING
RMN	81	Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping

0 of 9 row(s) selected.