Transfer learning reuses knowledge from models trained on large datasets to improve learning on new tasks with limited data. Originally validated on vision models pretrained on ImageNet, the paradigm now spans NLP (BERT, GPT), multimodal systems (CLIP), and domain-specific applications. Rather than training from scratch, you leverage pretrained weights as initialization, freeze or fine-tune layers selectively, and adapt to target tasks efficiently. The key insight: lower layers learn general features (edges, syntax) while upper layers capture task-specific patterns — selective unfreezing and discriminative learning rates exploit this hierarchy to avoid catastrophic forgetting and negative transfer when source and target domains differ.