Learning to Classify With Incremental New Class

Da-Wei Zhou

doi:10.1109/TNNLS.2021.3104882

2022-06-01

PRE

Da-Wei Zhou

Yang Yang *

De‐Chuan Zhan

DOI：10.1109/TNNLS.2021.3104882

原文链接

摘要

En 中文

New class detection and effective model expansion are of great importance in incremental data mining. In open incremental data environments, data often come with novel classes, e.g., the emergence of new classes in image classification or new topics in opinion monitoring, and is denoted as class-incremental learning (C-IL) in literature. There are two main challenges in C-IL: how to conduct novelty detection and how to update the model with few novel class instances. Most previous methods pay much attention to the former challenge while ignoring the problem of efficiently updating models. To solve this problem, we propose a novel framework to handle the incremental new class, named learning to classify with incremental new class (LC-INC), which can process these two challenges automatically in one unified framework. In detail, LC-INC utilizes a novel structure network to consider the prototype information between class centers of known classes and newly incoming instances, which can dynamically combine the prediction information with structure information to detect novel class instances efficiently. On the other hand, the proposed structure network can also act as a meta-network, which can learn to expand the model much faster and more efficiently with inadequate novel class instances. Experiments on synthetic and real-world datasets successfully validate the effectiveness of our proposed method.

Keyword:

Data stream classification

model adaptation

novel class detection

novelty detection