ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation

Antoine Saporta  Tuan-Hung Vu   Matthieu Cord   Patrick Pérez

CVPRW 2020

Abstract

While fully-supervised deep learning yields good models for urban scene semantic segmentation, these models struggle to generalize to new environments with different lighting or weather conditions for instance. In addition, producing the extensive pixel-level annotations that the task requires comes at a great cost. Unsupervised domain adaptation (UDA) is one approach that tries to address these issues in order to make such systems more scalable. In particular, self-supervised learning (SSL) has recently become an effective strategy for UDA in semantic segmentation. At the core of such methods liespseudo-labeling', that is, the practice of assigning high-confident class predictions as pseudo-labels, subsequently used as true labels, for target data. To collect pseudo-labels, previous works often rely on the highest softmax score, which we here argue as an unfavorable confidence measurement.

BibTeX

@inproceedings{saporta2020esl,
  title={Esl: Entropy-guided self-supervised learning for domain adaptation in semantic segmentation},
  author={Saporta, Antoine and Vu, Tuan-Hung and Cord, Matthieu and P{\'e}rez, Patrick},
  booktitle={CVPRW},
  year={2020}
}