用伪标签提升小样本下ViT性能，关键在何时引入而非如何生成。
Semi-Supervised Masked Autoencoders: Unlocking Vision Transformer Potential with Limited Data
- 联合重建与分类任务，动态启用高置信度伪标签。
- 在10%标签下比监督ViT高9.24%，优于MAE微调。
- 适合数据稀缺场景，尤其对小样本视觉模型训练有帮助。
当标注数据稀缺而无标注数据丰富时，我们提出半监督掩码自编码器（SSMAE），通过同时利用未标注和标注样本，结合动态选择的伪标签来联合优化掩码图像重建与分类。SSMAE引入验证驱动的门控机制，在模型对同一图像的弱增强和强增强视图均产生一致且高置信度预测后才激活伪标签，有效降低确认偏差。在CIFAR-10和CIFAR-100上，SSMAE始终优于监督式ViT和微调的MAE，尤其在低标签率下表现突出：在仅10%标签时，相比监督式ViT在CIFAR-10上提升9.24%。结果表明，伪标签引入时机与生成方式同样重要，是实现高效变压器训练的关键。代码已开源：https://github.com/atik666/ssmae。
原文摘要 · Abstract (English)
We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image reconstruction and classification using both unlabeled and labeled samples with dynamically selected pseudo-labels. SSMAE introduces a validation-driven gating mechanism that activates pseudo-labeling only after the model achieves reliable, high-confidence predictions that are consistent across both weakly and strongly augmented views of the same image, reducing confirmation bias. On CIFAR-10 and CIFAR-100, SSMAE consistently outperforms supervised ViT and fine-tuned MAE, with the largest gains in low-label regimes (+9.24% over ViT on CIFAR-10 with 10% labels). Our results demonstrate that when pseudo-labels are introduced is as important as how they are generated for data-efficient transformer training. Codes are available at https://github.com/atik666/ssmae.
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。