通过聚焦可能类别提升模型预测准确率，无需额外训练或数据增强。
Focus on Likely Classes for Test-Time Prediction
- 测试时聚焦高概率类别，利用类间共享特征优化预测
- 单次大步长梯度更新使不确定样本准确率显著提升
- 适用于各类文本与图像模型，尤其适合低置信度预测
我们探讨：在单一领域样本中聚焦可能类别是否能改善模型预测？以往研究认为否。本文提出新思路支持“是”：类间特征共享程度反映其对单个样本的可靠性。我们不依赖人工增强或辅助任务，提出两种新型测试时微调方法，以改进不确定预测。不同于直接选择最可能类别，新增“聚焦可能类别”步骤，当初始前向传播显示高不确定性时，采用大学习率进行一次梯度下降更新，以优化预测结果。实验表明，其中一种方法在多种文本与图像模型上平均实现准确率提升，验证了共享特征的重要性。
原文摘要 · Abstract (English)
We ask: Can focusing on likely classes of a single, in-domain sample improve model predictions? Prior work argued ``no''. We put forward a novel rationale in favor of ``yes'': Sharedness of features among classes indicates their reliability for a single sample. We aim for an affirmative answer without using hand-engineered augmentations or auxiliary tasks. We propose two novel test-time fine-tuning methods to improve uncertain model predictions. Instead of greedily selecting the most likely class, we introduce an additional step, \emph{focus on the likely classes}, to refine predictions. By applying a single gradient descent step with a large learning rate, we refine predictions when an initial forward pass indicates high uncertainty. The experimental evaluation demonstrates accuracy gains for one of our methods on average, which emphasizes shared features among likely classes. The gains are confirmed across diverse text and image domain models.
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。