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

TL;DR

ECOCSeg introduces an error-correcting code approach to semantic segmentation, enhancing pseudo-label quality and model robustness in label-scarce scenarios like UDA and SSL.

Contribution

The paper proposes ECOCSeg, a novel encoding-based framework that improves pseudo-label accuracy and model stability by using error-correcting output codes in segmentation.

Findings

Significant performance improvements on multiple UDA benchmarks.

Enhanced robustness and generalization in pseudo-label learning.

Easy integration with existing segmentation methods.

Abstract

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.