mlsanityData to 7 Oct 2026

A Simple Approach for Zero-Shot Learning based on Triplet Distribution Embeddings

arXiv 2103.15939 ↗First posted 29 Mar 2021cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Given the semantic descriptions of classes, Zero-Shot Learning (ZSL) aims to recognize unseen classes without labeled training data by exploiting semantic information, which contains knowledge between seen and unseen classes. Existing ZSL methods mainly use vectors to represent the embeddings to the semantic space. Despite the popularity, such vector representation limits the expressivity in terms of modeling the intra-class variability for each class. We address this issue by leveraging the use of distribution embeddings. More specifically, both image embeddings and class embeddings are modeled as Gaussian distributions, where their similarity relationships are preserved through the use of triplet constraints. The key intuition which guides our approach is that for each image, the embedding of the correct class label should be closer than that of any other class label. Extensive experiments on multiple benchmark data sets show that the proposed method achieves highly competitive results for both traditional ZSL and more challenging Generalized Zero-Shot Learning (GZSL) settings.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 52 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

29 of 52 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014Going Deeper with Convolutionscited by 4,231
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  7. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  8. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  9. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  10. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  11. 2015Label-Embedding for Image Classificationcited by 164
  12. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
17 more
  1. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  2. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  3. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  4. 2016Latent Embeddings for Zero-shot Classificationcited by 129
  5. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
  6. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  7. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  8. 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
  9. 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
  10. 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
  11. 2017Learning Robust Visual-Semantic Embeddingscited by 56
  12. 2017A Simple Exponential Family Framework for Zero-Shot Learningcited by 38
  13. 2019Creativity Inspired Zero-Shot Learningcited by 27
  14. 2016Gaze Embeddings for Zero-Shot Image Classificationcited by 25
  15. 2016Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classificationcited by 22
  16. 2018Towards Effective Deep Embedding for Zero-Shot Learningcited by 19
  17. 2019A Generative Framework for Zero-Shot Learning with Adversarial Domain Adaptationcited by 8

Built on by

Not cited yet.