AI RESEARCH
Class Incremental Learning with Task-Specific Batch Normalization and Out-of-Distribution Detection
arXiv CS.LG
•
ArXi:2411.00430v2 Announce Type: replace This study focuses on incremental learning for image classification, exploring how to reduce catastrophic forgetting of all learned knowledge when access to old data is restricted. The challenge lies in balancing plasticity (learning new knowledge) and stability (retaining old knowledge). Based on whether the task identifier (task-ID) is available during testing, incremental learning is divided into task incremental learning (TIL) and class incremental learning.