📒
📒
📒
📒
Machine & Deep Learning Compendium
Search
⌃K

Semi Supervised

  1. 1.
    ​Paper review​
  2. 2.
    ​Ruder an overview of proxy labeled for semi supervised (AMAZING)​
  3. 3.
    Self training
    1. 1.
      ​Self training and tri training​
    2. 2.
      ​Confidence regularized self training​
    3. 3.
      ​Domain adaptation for semantic segmentation using class balanced self-training​
    4. 4.
      ​Self labeled techniques for semi supervised learning​
  4. 4.
    Tri training
    1. 1.
      ​Trinet for semi supervised Deep learning​
    2. 2.
      ​Tri training exploiting unlabeled data using 3 classes, paper​
    3. 3.
      ​Improving tri training with unlabeled data​
    4. 4.
      ​Tri training using NN ensemble​
    5. 5.
      ​Asymmetric try training for unsupervised domain adaptation, another implementation, another, paper​
    6. 6.
      ​Tri training git​
  5. 5.
    ​Fast ai forums​
  6. 6.
    ​UDA GIT, paper, medium*, medium 2 (has data augmentation articles)​
  7. 7.
    ​s4l​
  8. 8.
    ​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).
  1. 1.
    ​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
  2. 2.
    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”
  3. 3.
    ​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​
  4. 4.
    ​Curriculum Labeling: Self-paced Pseudo-Labeling for Semi-Supervised Learning​
  5. 5.
    ​FAIR 2 original, Summarization of FAIR’s student teacher weak/ semi supervision​
  6. 6.
    ​Leveraging Just a Few Keywords for Fine-Grained Aspect Detection Through Weakly Supervised Co-Training​
  7. 7.
    ​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."
  8. 8.
    ​Unproven student teacher git​
  9. 9.
    ​A really nice student teacher git with examples.
Image by yuanli2333. wrong credit? let me know​
Image by the late Dr. Hui Li, @ SAS. wrong credit? let me know​
Types Of Machine Learning - Previous
Weakly Supervised
Next - Types Of Machine Learning
Active Learning
Last modified 1yr ago