Semi Supervised

​Paper review​
​Ruder an overview of proxy labeled for  semi supervised (AMAZING)​
Self training
​Self training and tri training​
​Confidence regularized self training​
​Domain adaptation for semantic segmentation using class balanced self-training​
​Self labeled techniques for semi supervised learning​
Tri training
​Trinet for semi supervised Deep learning​
​Tri training exploiting unlabeled data using 3 classes, paper​
​Improving tri training with unlabeled data​
​Tri training using NN ensemble​
​Asymmetric try training for unsupervised domain adaptation, another implementation, another, paper​
​Tri training git​
​Fast ai forums​
​UDA GIT, paper, medium*, medium 2 (has data augmentation articles)​
​s4l​
​Google’s UDM and MixMatch dissected- For text classification, the authors used a combination of back translation and a new method called TF-IDF based word replacing.
Back translation consists of translating a sentence into some other intermediate language (e.g. French) and then translating it back to the original language (English in this case). The authors trained an English-to-French and French-to-English system on the WMT 14 corpus.
TF-IDF word replacement replaces words in a sentence at random based on the TF-IDF scores of each word (words with a lower TF-IDF have a higher probability of being replaced).
​MixMatch, medium, 2, 3, 4, that works by guessing low-entropy labels for data-augmented unlabeled examples and mixing labeled and unlabeled data using MixUp. We show that MixMatch obtains state-of-the-art results by a large margin across many datasets and labeled data amounts
ReMixMatch - paper is really good. “We improve the recently-proposed “MixMatch” semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring”
​FixMatch - FixMatch is a recent semi-supervised approach by Sohn et al. from Google Brain that improved the state of the art in semi-supervised learning(SSL). It is a simpler combination of previous methods such as UDA and ReMixMatch.
​
Image via Amit Chaudhary wrong credit? let me know​
​Curriculum Labeling: Self-paced Pseudo-Labeling for Semi-Supervised Learning​
​FAIR 2 original, Summarization of FAIR’s student teacher weak/ semi supervision​
​Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training​
​Fidelity-Weighted Learning - “fidelity-weighted learning” (FWL), a semi-supervised student- teacher approach for training deep neural networks using weakly-labeled data. FWL modulates the parameter updates to a student network (trained on the task we care about) on a per-sample basis according to the posterior confidence of its label-quality estimated by a teacher (who has access to the high-quality labels). Both student and teacher are learned from the data."
​Unproven student teacher git​
​A really nice student teacher git with examples.
Image by yuanli2333. wrong credit? let me know​
Teacher student for tri training for unlabeled data exploitation​
Image by the late Dr. Hui Li, @ SAS. wrong credit? let me know​
Weakly Supervised
Regression
Last modified 5mo ago
Copy link