BriefGPT.xyz
Dec, 2021
模拟神谕:一种用于类别增量学习的初始相位去相关方法
Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning
HTML
PDF
Yujun Shi, Kuangqi Zhou, Jian Liang, Zihang Jiang, Jiashi Feng...
TL;DR
本研究提出了一种新的CIL学习方法,称为CwD,其中通过有效地规范每个类的表示来使其更均匀地分散,从而提高了现有最先进方法的性能约1%至3%。
Abstract
class incremental learning
(CIL) aims at learning a
multi-class classifier
in a phase-by-phase manner, in which only data of a subset of the classes are provided at each phase. Previous works mainly focus on miti
→