基于多臂老虎机的自适应数据增强：面向隐式模式识别的样本高效嵌入校准
Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition
在冻结的视觉/多模态嵌入模型之上训练轻量校准器，并用多臂老虎机驱动的自适应数据增强缓解少样本下的梯度漂移，可直接用于长尾识别、少样本分类等视觉下游任务的低成本适配。
原文依据 ADAMAB trains embedder-agnostic light-weight calibrators on top of fixed embedding models without accessing their parameters
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论识别视觉与文本模式在现代人工智能的许多实际应用中至关重要。然而，对于当前的大语言模型与视觉语言模型等预训练基础模型而言，处理长尾模式识别任务仍然颇具挑战。尽管微调预训练模型可以提升对此类隐式模式的识别准确率，但通常由于训练数据匮乏与计算开销高昂而难以实施。本文提出 ADAMAB，一个面向少样本模式识别的高效嵌入校准框架。为最大程度降低计算成本，ADAMAB 在固定的嵌入模型之上训练与嵌入器无关的轻量校准器，且不访问其参数。为缓解对大规模训练数据的需求，我们引入一种基于多臂老虎机机制的自适应数据增强策略。借助改进的上置信界算法，ADAMAB 减轻了梯度漂移，并在少样本训练中提供理论保证的收敛性。我们的多模态实验验证了 ADAMAB 的优越性能：在每类初始数据样本少于 5 个的条件下训练时，准确率提升最高可达 40%。
英文原文摘要 1194 字符
Recognizing visual and textual patterns is essential in many real-world applications of modern AI. However, tackling long-tail pattern recognition tasks remains challenging for current pre-trained foundation models such as LLMs and VLMs. While finetuning pre-trained models can improve accuracy in recognizing such implicit patterns, it is usually infeasible due to a lack of training data and high computational overhead. In this paper, we propose ADAMAB, an efficient embedding calibration framework for few-shot pattern recognition. To maximally reduce the computational costs, ADAMAB trains embedder-agnostic light-weight calibrators on top of fixed embedding models without accessing their parameters. To mitigate the need for large-scale training data, we introduce an adaptive data augmentation strategy based on the Multi-Armed Bandit (MAB) mechanism. With a modified upper confidence bound algorithm, ADAMAB diminishes the gradient shifting and offers theoretically guaranteed convergence in few-shot training. Our multi-modal experiments justify the superior performance of ADAMAB, with up to 40% accuracy improvement when training with less than 5 initial data samples of each class.