提出MLPMatch框架，用多层级扰动提升半监督语义分割性能。
Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation
- 设计多层级扰动机制，结合输入、特征与网络层扰动
- 在Pascal VOC和Cityscapes上达当前最佳效果
- 适合追求高精度分割的算法研究者
在半监督语义分割（SSS）中，弱-强一致性正则化技术被广泛采用，通常结合输入级和特征级扰动。然而，弱-强一致性正则化与网络扰动的融合仍较罕见。我们发现现有网络扰动在SSS中存在若干问题，可能为此现象的原因。通过重新审视网络扰动，我们提出一种新的网络扰动方法，以扩展对未标记数据的弱-强一致性正则化。此外，我们提出一种针对标记数据的波动学习过程，这在现有研究中较为少见。在已有输入级和特征级扰动的基础上，我们提出了MLPMatch（多层级扰动匹配）框架，该框架易于实现且高效。MLPMatch在Pascal VOC和Cityscapes数据集上得到验证，达到当前最优性能。代码已公开于https://github.com/LlistenL/MLPMatch。
原文摘要 · Abstract (English)
In semi-supervised semantic segmentation (SSS), weak-to-strong consistency regularization techniques are widely utilized in recent works, typically combined with input-level and feature-level perturbations. However, the integration between weak-to-strong consistency regularization and network perturbation has been relatively rare. We note several problems with existing network perturbations in SSS that may contribute to this phenomenon. By revisiting network perturbations, we introduce a new approach for network perturbation to expand the existing weak-to-strong consistency regularization for unlabeled data. Additionally, we present a volatile learning process for labeled data, which is uncommon in existing research. Building upon previous work that includes input-level and feature-level perturbations, we present MLPMatch (Multi-Level-Perturbation Match), an easy-to-implement and efficient framework for semi-supervised semantic segmentation. MLPMatch has been validated on the Pascal VOC and Cityscapes datasets, achieving state-of-the-art performance. Code is available from https://github.com/LlistenL/MLPMatch.
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。