Class Incremental

Class-incremental learning (CIL) focuses on training machine learning models that can continuously learn new classes of data without forgetting previously learned information, a challenge known as catastrophic forgetting. Current research emphasizes mitigating this forgetting through techniques like contrastive learning, hyperbolic embeddings, and knowledge distillation, often within the context of few-shot learning where limited data is available for new classes. This area is crucial for developing robust AI systems capable of adapting to evolving real-world data streams in applications such as autonomous driving and audio processing, where continuous learning is essential.