Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective

Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semi-supervised 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.

Authors

• Wangkai Li Deep Space Exploration Laboratory, University of Science and Technology of China
• Rui Sun Deep Space Exploration Laboratory, University of Science and Technology of China
• Zhaoyang Li University of California, San Diego
• Tianzhu Zhang Deep Space Exploration Laboratory, University of Science and Technology of China Institute of Artificial Intelligence, Hefei Comprehensive National Science Center

Keywords

No keywords are indexed for this paper.