Compensating Visual Insufficiency with Stratified Language Guidance for Long-Tail Class Incremental Learning

ArXi:2603.21708v1 Announce Type: new Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced data distributions. To tackle these issues, we exploit the informativeness and scalability of language knowledge.