让自监督模型在测试时持续优化，无需依赖预训练模型。
When Test-Time Adaptation Meets Self-Supervised Models
- 设计自监督测试时适应协议，解决低源域准确率下的适应难题。
- 在DINO、MoCo、iBOT上实现与有预训练相当的性能提升。
- 融合对比学习与知识蒸馏，适合动态环境中的自监督部署。
在测试时使用测试数据进行训练，可使深度学习模型适应动态环境变化，提升实际应用能力。从源域到目标域的在线适应虽有前景，但高度依赖源预训练模型的性能。本文探究测试时适应（TTA）方法是否能在不依赖源预训练的前提下，持续改进自监督学习（SSL）模型。我们发现，现有TTA方法在源域准确率较低的自监督模型上表现不佳，因此提出一种自监督测试时适应协议。进一步构建协同学习框架，融合对比学习与知识蒸馏，实现表征的逐步优化。在DINO、MoCo、iBOT等多样自监督模型上，于多个TTA基准测试中验证了方法的有效性。实验表明，该方法在无源预训练条件下仍能取得竞争力性能。
原文摘要 · Abstract (English)
Training on test-time data enables deep learning models to adapt to dynamic environmental changes, enhancing their practical applicability. Online adaptation from source to target domains is promising but it remains highly reliant on the performance of source pretrained model. In this paper, we investigate whether test-time adaptation (TTA) methods can continuously improve models trained via self-supervised learning (SSL) without relying on source pretraining. We introduce a self-supervised TTA protocol after observing that existing TTA approaches struggle when directly applied to self-supervised models with low accuracy on the source domain. Furthermore, we propose a collaborative learning framework that integrates SSL and TTA models, leveraging contrastive learning and knowledge distillation for stepwise representation refinement. We validate our method on diverse self-supervised models, including DINO, MoCo, and iBOT, across TTA benchmarks. Extensive experiments validate the effectiveness of our approach in SSL, showing that it achieves competitive performance even without source pretraining.
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。