Publication Type
Journal Article
Version
acceptedVersion
Publication Date
3-2026
Abstract
Class incremental learning (CIL) aims to learn a model that can not only incrementally accommodate new classes, but also maintain the learned knowledge of old classes. Out-of-distribution (OOD) detection in CIL is to retain this incremental learning ability, while being able to reject unknown samples that are drawn from different distributions of the learned classes. This capability is crucial to the safety of deploying CIL models in open worlds. However, despite remarkable advancements in the respective CIL and OOD detection, there lacks a systematic and large-scale benchmark to assess the capability of advanced CIL models in detecting OOD samples. To fill this gap, in this study we design a comprehensive empirical study to establish such a benchmark, named OpenCIL, offering a unified protocol for enabling CIL models with different OOD detectors using two principled OOD detection frameworks. One key observation we find through our comprehensive evaluation is that the CIL models can be severely biased towards the OOD samples and newly added classes when they are exposed to open environments. Motivated by this, we further propose a novel approach for OOD detection in CIL, namely Bi-directional Energy Regularization (BER), which is specially designed to mitigate these two biases in different CIL models by having energy regularization on both old and new classes. Extensive experiments show that BER can substantially improve the OOD detection capability across a range of CIL models, achieving state-of-the-art performance on the OpenCIL benchmark. All codes and datasets are open-source at https://github.com/mala-lab/OpenCIL.
Keywords
Class incremental learning, Out-of-distribution detection
Discipline
Databases and Information Systems | Numerical Analysis and Scientific Computing | OS and Networks
Research Areas
Intelligent Systems and Optimization
Areas of Excellence
Digital transformation
Publication
Pattern Recognition
Volume
171
First Page
1
Last Page
17
ISSN
0031-3203
Identifier
10.1016/j.patcog.2025.112163
Publisher
Elsevier
Citation
MIAO, Wenjun; PANG, Guansong; NGUYEN, Trong-Tung; FANG, Ruohuan; ZHENG, Jin; and BAI, Xiao.
OpenCIL: Benchmarking out-of-distribution detection in class incremental learning. (2026). Pattern Recognition. 171, 1-17.
Available at: https://ink.library.smu.edu.sg/sis_research/10400
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1016/j.patcog.2025.112163
Included in
Databases and Information Systems Commons, Numerical Analysis and Scientific Computing Commons, OS and Networks Commons