.png){kind=icon}
.png){kind=icon}
Return
ORACIL: Conflict-Graph-Based Order-Robust Analytic Class-Incremental Learning
.png){kind=icon}
OA
AI
DOI：10.3390/electronics15132941.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Class-incremental learning allows a model to continuously acquire new classes from sequentially arriving data while preserving its ability to recognize previously learned ones, which is essential for improving adaptability and supporting long-term evolution. However, the class arrival order is inherently random, and highly similar classes may appear consecutively, which intensifies catastrophic forgetting. Although replay-based methods can effectively alleviate this problem, they usually require storing or accessing historical raw samples, which introduces additional data-retention and storage burdens. To address these challenges, this paper proposes ORACIL, an Order-Robust Analytic Class-Incremental Learning framework. First, ORACIL constructs a conflict graph based on class centroids and dynamically partitions newly arriving classes into multiple low-similarity groups, thereby reducing inter-class interference and mitigating forgetting. Second, for each class group, it trains an analytic incremental classification head and performs recursive closed-form updates for the analytic heads using current-stage data and accumulated second-order statistics, without replaying raw historical samples. For group recognition, ORACIL uses feature-derived distance representations rather than raw historical images, making the incremental process raw-sample-free with respect to original image replay. Third, during inference, the group probabilities generated by the group-recognition router are softly fused with the class scores produced by each analytic head, and the class with the highest fused probability is selected as the final prediction. Extensive experiments on CIFAR-100, CUB200, and OmniBenchmark demonstrate the effectiveness of ORACIL. Without replaying historical images, ORACIL achieves final-phase average forgetting rates of 0.16%, 0.77%, and 1.04%, and final-phase accuracies of 95.77%, 93.86%, and 88.12%, respectively. In addition, the MOPD and AOPD results show that ORACIL maintains strong robustness under different class arrival orders.
Keywords:
class-incremental learning
analytic learning
catastrophic forgetting
order robustness
raw-sample-free learning
replay-free learning