Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track
Yonatan Dukler, Alessandro Achille, Hao Yang, Varsha Vivek, Luca Zancato, Benjamin Bowman, Avinash Ravichandran, Charless Fowlkes, Ashwin Swaminathan, Stefano Soatto
We present a framework for transfer learning that efficiently adapts a large base-model by learning lightweight cross-attention modules attached to its intermediate activations.We name our approach InCA (Introspective-Cross-Attention) and show that it can efficiently survey a network’s representations and identify strong performing adapter models for a downstream task.During training, InCA enables training numerous adapters efficiently and in parallel, isolated from the frozen base model. On the ViT-L/16 architecture, our experiments show that a single adapter, 1.3% of the full model, is able to reach full fine-tuning accuracy on average across 11 challenging downstream classification tasks.Compared with other forms of parameter-efficient adaptation, the isolated nature of the InCA adaptation is computationally desirable for large-scale models. For instance, we adapt ViT-G/14 (1.8B+ parameters) quickly with 20+ adapters in parallel on a single V100 GPU (76% GPU memory reduction) and exhaustively identify its most useful representations.We further demonstrate how the adapters learned by InCA can be incrementally modified or combined for flexible learning scenarios and our approach achieves state of the art performance on the ImageNet-to-Sketch multi-task benchmark.