Andrea Maracani

continual learning (1) catastrophic forgetting (1) semantic segmentation (1) multi-task learning (1) transfer learning (1) text classification (1) knowledge distillation (1) named entity recognition (1) incremental learning (1) label noise (1) parameter-efficient fine-tuning (1) low-rank adaptation (1) generative adversarial network (1) parameter-efficient tuning (1) model scaling (1) parameter-efficient finetuning (1) scene text recognition (1) lightweight transformer (1) replay-based learning (1)