用少量无标签数据选最优模型，提升模型在新任务上的泛化能力。
Neural Coherence : Find higher performance to out-of-distribution tasks from few samples
- 基于激活统计的神经一致性，仅需少量目标域数据做模型选择。
- 在食品、植物、自然物种识别任务上显著优于传统方法。
- 适用于数据稀缺场景，尤其适合少样本和跨域迁移学习。
为应对下游任务中预训练大视觉模型微调时的模型选择难题，本文提出一种新方法：神经一致性（Neural Coherence）。该方法通过分析模型在源域与目标域的激活统计特征，实现仅用少量无标签目标样本即可高效选择最优模型检查点。实验基于ImageNet1K预训练模型，在Food-101、PlantNet-300K和iNaturalist等出域任务上验证，相比现有基线显著提升泛化性能。此外，该方法还被证明可有效用于训练数据筛选，展现出良好的通用性。
原文摘要 · Abstract (English)
To create state-of-the-art models for many downstream tasks, it has become common practice to fine-tune a pre-trained large vision model. However, it remains an open question of how to best determine which of the many possible model checkpoints resulting from a large training run to use as the starting point. This becomes especially important when data for the target task of interest is scarce, unlabeled and out-of-distribution. In such scenarios, common methods relying on in-distribution validation data become unreliable or inapplicable. This work proposes a novel approach for model selection that operates reliably on just a few unlabeled examples from the target task. Our approach is based on a novel concept: Neural Coherence, which entails characterizing a model's activation statistics for source and target domains, allowing one to define model selection methods with high data-efficiency. We provide experiments where models are pre-trained on ImageNet1K and examine target domains consisting of Food-101, PlantNet-300K and iNaturalist. We also evaluate it in many meta-learning settings. Our approach significantly improves generalization across these different target domains compared to established baselines. We further demonstrate the versatility of Neural Coherence as a powerful principle by showing its effectiveness in training data selection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。