mlsanityData to 14 Oct 2026

Semantic Borrowing for Generalized Zero-Shot Learning

arXiv 2102.04969 ↗First posted 30 Jan 2021cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Generalized zero-shot learning (GZSL) is one of the most realistic but challenging problems due to the partiality of the classifier to supervised classes, especially under the class-inductive instance-inductive (CIII) training setting, where testing data are not available. Instance-borrowing methods and synthesizing methods solve it to some extent with the help of testing semantics, but therefore neither can be used under CIII. Besides, the latter require the training process of a classifier after generating examples. In contrast, a novel non-transductive regularization under CIII called Semantic Borrowing (SB) for improving GZSL methods with compatibility metric learning is proposed in this paper, which not only can be used for training linear models, but also nonlinear ones such as artificial neural networks. This regularization item in the loss function borrows similar semantics in the training set, so that the classifier can model the relationship between the semantics of zero-shot and supervised classes more accurately during training. In practice, the information of semantics of unknown classes would not be available for training while this approach does NOT need it. Extensive experiments on GZSL benchmark datasets show that SB can reduce the partiality of the classifier to supervised classes and improve the performance of generalized zero-shot classification, surpassing inductive GZSL state of the arts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 30 Jan 2021.

Builds on

18 of 32 references.

References · 18

  1. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  2. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
  3. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  4. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  5. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  6. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  7. 2015Label-Embedding for Image Classificationcited by 165
  8. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  9. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  10. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  11. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  12. 2016Latent Embeddings for Zero-shot Classificationcited by 129
6 more
  1. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  2. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  3. 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74
  4. 2015Transductive Multi-view Zero-Shot Learningcited by 53
  5. 2017Generating Visual Representations for Zero-Shot Classificationcited by 37
  6. 2018Towards Effective Deep Embedding for Zero-Shot Learningcited by 19

Built on by

Not cited yet.