Decoupled Certainty-Driven Consistency Loss for Semi-supervised Learning

By Lu Liu, Yiting Li, Robby T. Tan. 2019

19 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Andrew Tao
2. Bryan Catanzaro
3. Karan Sapra
4. Farhad Pourpanah
5. Moloud Abdar
6. Abbas Khosravi
7. Paul W. Fieguth
8. Eric Arazo

Citations in the corpus

• Hierarchical Multi-Scale Attention for Semantic Segmentation (2020, methodology): “Similar to [37, 4] we generate hard dense labels for the coarse Cityscapes images.”
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges (2020, background): “[239] presented a new certainty-driven consistency loss (CCL) that employed predictive uncertainty information in the consistency loss to learn students from reliable targets dynamically.”
• Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning (2019, methodology): “Consistency regularization and pseudo-labeling approaches apply different strategies such as a warm-up phase using labeled data [17, 18], uncertainty weighting [11, 19], adversarial attacks [20, 21], or graphconsistency [17, 22].”