Corpus ID: 220514779

Semi-supervised Learning with a Teacher-student Network for Generalized Attribute Prediction

  title={Semi-supervised Learning with a Teacher-student Network for Generalized Attribute Prediction},
  author={Minchul Shin},
  • Minchul Shin
  • Published 2020
  • Computer Science
  • ArXiv
  • This paper presents a study on semi-supervised learning to solve the visual attribute prediction problem. In many applications of vision algorithms, the precise recognition of visual attributes of objects is important but still challenging. This is because defining a class hierarchy of attributes is ambiguous, so training data inevitably suffer from class imbalance and label sparsity, leading to a lack of effective annotations. An intuitive solution is to find a method to effectively learn… CONTINUE READING


    Publications referenced by this paper.
    Label-Embedding for Image Classification
    • 300
    • Open Access
    Multi-Task CNN Model for Attribute Prediction
    • 153
    • Open Access
    Meta-Learning for Semi-Supervised Few-Shot Classification
    • 278
    • Open Access
    Zero-Shot Learning Through Cross-Modal Transfer
    • 898
    • Open Access
    Deep Metric Learning Using Triplet Network
    • 728
    • Open Access
    Prototypical Networks for Few-shot Learning
    • 1,471
    • Open Access
    Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
    • 348
    • Open Access
    Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network
    • 238
    • Highly Influential
    • Open Access
    Teaching Semi-Supervised Classifier via Generalized Distillation
    • 10
    • Open Access