TOAST：通过注意力引导的迁移学习
TOAST: Transfer Learning via Attention Steering
AI总结：
TOAST提出一种冻结骨干网络、通过选取任务相关特征并反馈以引导注意力的迁移学习方法，在细粒度视觉分类和指令跟随生成任务上以少量可调参数超越完全微调、LoRA和提示微调。
摘要：
迁移学习涉及将预训练模型适配到新的下游任务。然而，我们观察到当前的迁移学习方法往往未能聚焦于与任务相关的特征。在这项工作中，我们探索通过重新聚焦模型注意力来进行迁移学习。我们提出Top-Down Attention Steering（TOAST），这是一种新颖的迁移学习算法，它保持预训练骨干网络冻结，在输出中选取与任务相关的特征，并将这些特征反馈给模型，以将注意力引导至任务特定特征。仅通过重新聚焦注意力，TOAST在多个迁移学习基准上取得了最先进的结果，同时仅需少量可调参数。与完全微调、LoRA和提示微调相比，TOAST在一系列细粒度视觉分类数据集上显著提升了性能（例如，在FGVC上从81.1%提升到86.2%）。在指令跟随语言生成任务上，TOAST也优于完全微调的Alpaca和Vicuna模型。代码可在https://github.com/bfshi/TOAST获取。
英文摘要：
Transfer learning involves adapting a pre-trained model to novel downstream tasks. However, we observe that current transfer learning methods often fail to focus on task-relevant features. In this work, we explore refocusing model attention for transfer learning. We introduce Top-Down Attention Steering (TOAST), a novel transfer learning algorithm that keeps the pre-trained backbone frozen, selects task-relevant features in the output, and feeds those features back to the model to steer the attention to the task-specific features. By refocusing the attention only, TOAST achieves state-of-the-art results on a number of transfer learning benchmarks, while having a small number of tunable parameters. Compared to fully fine-tuning, LoRA, and prompt tuning, TOAST substantially improves performance across a range of fine-grained visual classification datasets (e.g., 81.1% -> 86.2% on FGVC). TOAST also outperforms the fully fine-tuned Alpaca and Vicuna models on instruction-following language generation. Code is available at https://github.com/bfshi/TOAST.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
