SEAL: Searching Expandable Architectures for Incremental Learning

SEAL is a newly introduced framework that integrates Neural Architecture Search (NAS) for data-incremental learning, addressing the challenge of balancing model plasticity and stability. It dynamically expands the model architecture only when necessary, guided by a capacity estimation metric, and employs cross-distillation training to mitigate forgetting. Experimental results show that SEAL improves accuracy and reduces resource usage, making it a promising approach for efficient incremental learning in resource-constrained environments.