Gradual self-training is a method for semi-supervised domain adaptation. The goal is to adapt an initial classifier trained on a source domain given only unlabeled data that shifts gradually in distribution towards a target domain.
This comes up for example in applications ranging from sensor networks and self-driving car perception modules to brain-machine interfaces, where machine learning systems must adapt to data distributions that evolve over time.
The gradual self-training algorithm begins with a classifier $w_0$ trained on labeled examples from the source domain (Figure a). For each successive domain $P_t$, the algorithm generates pseudolabels for unlabeled examples from that domain, and then trains a regularized supervised classifier on the pseudolabeled examples. The intuition, visualized in the Figure, is that after a single gradual shift, most examples are pseudolabeled correctly so self-training learns a good classifier on the shifted data, but the shift from the source to the target can be too large for self-training to correct.
Source: Understanding Self-Training for Gradual Domain AdaptationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Domain Adaptation | 4 | 14.81% |
Unsupervised Domain Adaptation | 4 | 14.81% |
Bilingual Lexicon Induction | 2 | 7.41% |
Cross-Lingual Word Embeddings | 2 | 7.41% |
Machine Translation | 2 | 7.41% |
Multilingual NLP | 2 | 7.41% |
Multilingual Word Embeddings | 2 | 7.41% |
Pretrained Multilingual Language Models | 2 | 7.41% |
Self-Learning | 2 | 7.41% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |