• DeCAF

  • Referenced in 27 articles [sw17856]
  • there may be insufficient labeled or unlabeled data to conventionally train or adapt a deep...
  • STL-10 dataset

  • Referenced in 23 articles [sw39164]
  • make use of the unlabeled data (which comes from a similar but different distribution from...
  • IMDB

  • Referenced in 16 articles [sw36449]
  • binary sentiment classification containing substantially more data than previous benchmark datasets. We provide ... testing. There is additional unlabeled data for use as well. Raw text and already processed...
  • MixMatch

  • Referenced in 6 articles [sw41280]
  • powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets ... unlabeled examples and mixing labeled and unlabeled data using MixUp. We show that MixMatch obtains...
  • PTE

  • Referenced in 7 articles [sw37756]
  • semi-supervised representation learning method for text data, which we call the extit{predictive text ... text embedding utilizes both labeled and unlabeled data to learn the embedding of text...
  • SpectralNet

  • Referenced in 6 articles [sw26162]
  • naturally generalizes the spectral embedding to unseen data points. To further improve the quality ... Gaussian affinities with affinities leaned from unlabeled data using a Siamese network. Additional improvement...
  • wav2vec

  • Referenced in 3 articles [sw38717]
  • training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates...
  • GSPPCA

  • Referenced in 5 articles [sw25977]
  • GSPPCA). Its usefulness is illustrated on synthetic data sets and on several real unsupervised feature ... processing and genomics. In particular, using unlabeled microarray data, GSPPCA is shown to infer biologically...
  • ALiPy

  • Referenced in 3 articles [sw33954]
  • many real applications, there are plentiful unlabeled data but limited labeled data; and the acquisition...
  • upclass

  • Referenced in 2 articles [sw25651]
  • which implement data classification. It uses unlabeled data to obtain parameter estimates of models...
  • SSentiA

  • Referenced in 1 article [sw39059]
  • supervised Sentiment Analyzer for classification from unlabeled data. In recent years, supervised machine learning ... obtain, thus, not always achievable. When annotated data are unavailable, the unsupervised tools are exercised ... performance of sentiment classification from unlabeled data. We present a self-supervised hybrid methodology SSentiA ... based method for sentiment classification from unlabeled data. We first introduce LRSentiA (Lexical Rule-based...
  • FixMatch

  • Referenced in 2 articles [sw41277]
  • provides an effective means of leveraging unlabeled data to improve a model’s performance ... model’s predictions on weakly-augmented unlabeled images. For a given image, the pseudo-label...
  • InfoGraph

  • Referenced in 2 articles [sw37754]
  • graph-level representations encode aspects of the data that are shared across different scales ... result, the supervised encoder learns from unlabeled data while preserving the latent semantic space favored...
  • ReMixMatch

  • Referenced in 2 articles [sw41275]
  • marginal distribution of predictions on unlabeled data to be close to the marginal distribution...
  • DDFlow

  • Referenced in 1 article [sw38829]
  • DDFlow: Learning Optical Flow with Unlabeled Data Distillation. We present DDFlow, a data distillation approach ... learning optical flow estimation from unlabeled data. The approach distills reliable predictions from a teacher...
  • Manifold Regularization

  • Referenced in 1 article [sw24840]
  • supervised framework that incorporates labeled and unlabeled data in a general-purpose learner. Some transductive ... supervised algorithms are able to use unlabeled data effectively. Finally we have a brief discussion...
  • VoxPopuli

  • Referenced in 1 article [sw39143]
  • multilingual corpus providing 100K hours of unlabelled speech data in 23 languages ... largest open data to date for unsupervised representation learning as well as semi-supervised learning ... validate the versatility of VoxPopuli unlabelled data in semi-supervised learning under challenging...
  • NuclearDiscrepancy

  • Referenced in 1 article [sw34692]
  • labeled given a pool of unlabeled data. Instead of selecting randomly what data to annotate...
  • DeeBNet

  • Referenced in 1 article [sw21888]
  • create a powerful generative model using training data. DBNs have many ability like feature extraction ... good representation of the input from unlabeled data with better discrimination between different classes. Also...
  • SUPERB

  • Referenced in 1 article [sw39134]
  • shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA...