学习什么有帮助：面向视觉任务的任务对齐上下文选择
Learning What Helps: Task-Aligned Context Selection for Vision Tasks
TACS 将检索选择器与任务模型联合训练，用任务奖励而非相似度来挑选上下文示例，为视觉任务中的检索增强提供了一种可复用的训练范式，尤其适用于数据有限或细粒度识别场景。
原文依据 TACS jointly trains a selector network with the task model through a hybrid optimization scheme combining gradient-based supervision and reinforcement learning, making retrieval part of the learning objective.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人类常通过将图像与相关示例进行比较来解决视觉不确定性，但视觉Transformer（ViT）缺乏识别哪些示例能改善其预测的能力。本文提出任务对齐上下文选择（TACS）框架，学习选择真正提升任务性能的配对示例，而非仅看似相似的示例。TACS通过结合基于梯度的监督和强化学习的混合优化方案，联合训练选择器网络与任务模型，使检索成为学习目标的一部分。通过将选择与任务奖励对齐，TACS使判别模型能够发现哪些上下文示例真正有帮助。在涵盖细粒度识别、医学图像分类和医学图像分割的18个数据集上，TACS始终优于基于相似度的检索，尤其在具有挑战性或数据有限的设置中。
英文原文摘要 922 字符
Humans often resolve visual uncertainty by comparing an image with relevant examples, but ViTs lack the ability to identify which examples would improve their predictions. We present Task-Aligned Context Selection (TACS), a framework that learns to select paired examples which truly improve task performance rather than those that merely appear similar. TACS jointly trains a selector network with the task model through a hybrid optimization scheme combining gradient-based supervision and reinforcement learning, making retrieval part of the learning objective. By aligning selection with task rewards, TACS enables discriminative models to discover which contextual examples genuinely help. Across 18 datasets covering fine-grained recognition, medical image classification, and medical image segmentation, TACS consistently outperforms similarity-based retrieval, particularly in challenging or data-limited settings.