Learning to Classify With Incremental New Class

By Da-Wei Zhou, Yang Yang, De-chuan Zhan. 2021

73 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Qiwen Wang
5. Ziwei Liu
6. Fu-Yun Wang
7. Zhi-Hong Qi
8. Shiliang Pu

Citations in the corpus

• FOSTER: Feature Boosting and Compression for Class-Incremental Learning (2022, background): “The real world is constantly changing, with new concepts and categories continuously springing up [14,35,46,48].”
• Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks (2022, background): “However, real-world applications often face the stream format data [7] and novel classes [8], [9], [10], [11], [12], e.”
• Forward Compatible Few-Shot Class-Incremental Learning (2022, background): “However, data often come in stream format [18] with emerging new classes [12, 63, 65] in real-world applications, e.”
• A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning (2022, background): “In the open world, training data is often collected in stream format with new classes appearing [16, 15, 63, 65].”
• Deep Class-Incremental Learning: A Survey (2023, background): “CIL with Complex Inputs: In the real world, data is often with complex format [202], [203], e.”