用大模型零样本伪标签提升小数据场景下的学习效果
Enhancing Semi-supervised Learning with Zero-shot Pseudolabels
- 结合知识蒸馏与一致性学习，融合标注数据、无标注数据和大模型伪标签
- 在6个视觉语言分类任务上均超越传统半监督方法，稳定提升性能
- 仅需大模型推理即可训练轻量学生模型，适合手机等低算力设备
数据标注成本高昂，制约了机器学习系统的规模化部署。半监督学习（SSL）通过结合少量标注数据与大量无标注数据缓解该问题。近年来基础模型（FMs）的出现提供了强大的零样本能力，进一步降低标注需求。然而，在资源受限环境下直接微调大型基础模型往往不切实际，且直接使用其伪标签可能导致性能下降，原因在于标签不可靠或与目标任务领域不匹配。本文提出ZeroMatch，一种新型半监督学习框架，将知识蒸馏与一致性学习相结合，协同利用标注数据、无标注数据以及来自基础模型的伪标签。该方法仅通过基础模型推理即可训练轻量级学生模型，适用于计算资源有限的场景（如个人设备）。在六个视觉与语言分类基准上的实验表明，ZeroMatch在不同质量的基础模型下均持续优于标准半监督学习及零样本增强方法，展现出出色的性能与鲁棒性。
原文摘要 · Abstract (English)
The high cost of data labeling presents a major barrier to deploying machine learning systems at scale. Semi-supervised learning (SSL) mitigates this challenge by utilizing unlabeled data alongside limited labeled examples, while the emergence of foundation models (FMs) offers powerful zero-shot capabilities that can further reduce labeling cost. However, directly fine-tuning large FMs is often impractical in resource-constrained settings, and naïvely using their pseudo-labels for unlabeled data can degrade performance due to its unreliablity or domain mismatch with target task. In this work, we introduce ZeroMatch, a novel SSL framework that integrates knowledge distillation with consistency-based learning to jointly leverage labeled data, unlabeled data, and pseudo-labels from FMs. ZeroMatch enables training compact student models using only FM inference, making it suitable for low-resource environments such as personal devices with limited compute. Experiments on six vision and language classification benchmarks show that ZeroMatch consistently outperforms standard SSL and zero-shot augmented methods, demonstrating its effectiveness and robustness across a range of foundation model qualities.
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。