ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation
By Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez. 2020
50 citations recorded by the source corpus.
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 lies `pseudo-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. In this work, we propose Entropy-guided Self-supervised Learning (ESL), leveraging entropy as the confidence indicator for producing more accurate pseudo-labels. On different UDA benchmarks, ESL consistently outperforms strong SSL baselines and achieves state-of-the-art results.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Arthur Douillard
- Matthieu Cord
- Yifu Chen
- Arnaud Dapogny
- Timothée Lesort
- Fabio Cermelli
- Beomyoung Kim
- Francesco Pelosin
In Computer Vision and Pattern Recognition
- Arthur Douillard
- Matthieu Cord
- Yifu Chen
- Arnaud Dapogny
- Bernt Schiele
- Luc Van Gool
- Fabio Cermelli
- Joost van de Weijer
Citations in the corpus
- PLOP: Learning without Forgetting for Continual Semantic Segmentation (2020, methodology): “Pseudo-labeling [39] is commonly used in domain adaptation for semantic segmentation [63, 41, 79, 58], where a model is trained on the union of real labels of a source dataset and pseudo labels assigned to an unlabeled target dataset.”