Selective Backpropagation for Efficient Few-Shot Class-Incremental Learning
Few-Shot Class-Incremental Learning (FSCIL) requires models to continuously learn new classes from limited samples while retaining prior knowledge, under strict constraints on compute and memory. Existing approaches lie along a difficult trade-off: simple fine-tuning is computationally efficient but suffers from catast...
Eeham Khan, Abdulmoumen Al-Atrash, Ali Ayub
· 0 citations