通过分类局部图像块提升去噪自编码器的表征能力
DenoMAE2.0: Improving Denoising Masked Autoencoders by Classifying Local Patches
- 新增局部图像块分类任务，结合重建损失增强特征学习
- 在低信噪比和小数据下，分类准确率提升超16%
- 适合无线信号识别等噪声大、数据少的场景
我们提出DenoMAE2.0，一种改进的去噪掩码自编码器，通过引入局部图像块分类目标与传统重建损失相结合，提升表征学习能力和鲁棒性。与仅关注输入重建的传统掩码自编码器不同，DenoMAE2.0对未掩码块进行位置感知分类，使模型能够捕捉细粒度局部特征并保持全局一致性。该双目标方法在无线通信的半监督学习中表现突出，尤其适用于高噪声和数据稀缺场景。我们在广泛信噪比（SNR）范围（从极低到中等）及小数据环境下对调制信号分类进行了大量实验。结果表明，DenoMAE2.0优于其前身Deno-MAE及其他基线模型，在去噪质量和下游分类准确率上均有提升：在自建数据集上较DenoMAE提升1.1%；在RadioML基准上，星座图分类准确率分别提升11.83%和16.55%。
原文摘要 · Abstract (English)
We introduce DenoMAE2.0, an enhanced denoising masked autoencoder that integrates a local patch classification objective alongside traditional reconstruction loss to improve representation learning and robustness. Unlike conventional Masked Autoencoders (MAE), which focus solely on reconstructing missing inputs, DenoMAE2.0 introduces position-aware classification of unmasked patches, enabling the model to capture fine-grained local features while maintaining global coherence. This dual-objective approach is particularly beneficial in semi-supervised learning for wireless communication, where high noise levels and data scarcity pose significant challenges. We conduct extensive experiments on modulation signal classification across a wide range of signal-to-noise ratios (SNRs), from extremely low to moderately high conditions and in a low data regime. Our results demonstrate that DenoMAE2.0 surpasses its predecessor, Deno-MAE, and other baselines in both denoising quality and downstream classification accuracy. DenoMAE2.0 achieves a 1.1% improvement over DenoMAE on our dataset and 11.83%, 16.55% significant improved accuracy gains on the RadioML benchmark, over DenoMAE, for constellation diagram classification of modulation signals.
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。