用纠错编码提升伪标签质量，让分割模型更鲁棒。
Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective
- 用纠错编码替代独热码，拆解类别属性，抗部分错误
- 比特级去噪机制生成更高质量伪标签，提升监督信号
- 可无缝接入现有方法，适配多种分割架构与场景
伪标签学习广泛应用于语义分割，尤其在标签稀缺场景如无监督域适应（UDA）和半监督学习（SSL）中。尽管成效显著，该范式常产生错误伪标签，且因采用独热编码导致错误在训练中被放大。为此，我们提出ECOCSeg，一种基于纠错输出码（ECOC）的新型分割建模视角，为每类构建细粒度编码。该方法具有多重优势：首先，引入基于ECOC的分类器，使模型能将类别分解为属性，容忍部分误码，增强伪标签学习中的稳定性和泛化能力；其次，设计比特级标签去噪机制，生成更高质量伪标签，为无标签图像提供充分且稳健的监督信号。ECOCSeg可轻松集成至现有方法，在多个UDA与SSL基准上，针对不同分割架构均实现显著性能提升。代码已开源：https://github.com/Woof6/ECOCSeg。
原文摘要 · Abstract (English)
Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL). Despite its success, this paradigm can generate erroneous pseudo-labels, which are further amplified during training due to utilization of one-hot encoding. To address this issue, we propose ECOCSeg, a novel perspective for segmentation models that utilizes error-correcting output codes (ECOC) to create a fine-grained encoding for each class. ECOCSeg offers several advantages. First, an ECOC-based classifier is introduced, enabling model to disentangle classes into attributes and handle partial inaccurate bits, improving stability and generalization in pseudo-label learning. Second, a bit-level label denoising mechanism is developed to generate higher-quality pseudo-labels, providing adequate and robust supervision for unlabeled images. ECOCSeg can be easily integrated with existing methods and consistently demonstrates significant improvements on multiple UDA and SSL benchmarks across different segmentation architectures. Code is available at https://github.com/Woof6/ECOCSeg.
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。