Certainty-Driven Consistency Loss for Semi-supervised Learning

13 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.

Self-Training With Noisy Student Improves ImageNet Classification (2019, background): “Apart from self-training, another important line of work in semi-supervised learning [11, 96] is based on consistency training [5, 60, 43, 79, 52, 48, 58, 12, 15, 56, 2, 45, 82, 84, 7, 91].”
ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation (2020, methodology): “driven toward low-density regions in the target space. One major concern of training with pseudo-labels is the lack of guarantee for label correctness, which may eventually cause a “conﬁrmation bias” [13,21], namely models are biased to previous incorrect pseudo-labels and resist new changes. To add”
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning (2019, methodology): “ed) to deal, respectively, with the network predictions not being equally conﬁdent over all unlabeled samples and with the class-imbalance problem. It is important to highlight a widely used practice [27, 13, 31, 25, 16, 10]: a warm-up where labeled samples have a higher (or full) weight at the begi”