mlsanityData to 7 Oct 2026

Cluster-based Contrastive Disentangling for Generalized Zero-Shot Learning

arXiv 2203.02648 ↗First posted 5 Mar 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Generalized Zero-Shot Learning (GZSL) aims to recognize both seen and unseen classes by training only the seen classes, in which the instances of unseen classes tend to be biased towards the seen class. In this paper, we propose a Cluster-based Contrastive Disentangling (CCD) method to improve GZSL by alleviating the semantic gap and domain shift problems. Specifically, we first cluster the batch data to form several sets containing similar classes. Then, we disentangle the visual features into semantic-unspecific and semantic-matched variables, and further disentangle the semantic-matched variables into class-shared and class-unique variables according to the clustering results. The disentangled learning module with random swapping and semantic-visual alignment bridges the semantic gap. Moreover, we introduce contrastive learning on semantic-matched and class-unique variables to learn high intra-set and intra-class similarity, as well as inter-set and inter-class discriminability. Then, the generated visual features conform to the underlying characteristics of general images and have strong discriminative information, which alleviates the domain shift problem well. We evaluate our proposed method on four datasets and achieve state-of-the-art results in both conventional and generalized settings.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 46 references that are in the map. First posted on arXiv 5 Mar 2022.

Builds on

33 of 46 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  8. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  9. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  10. 2018Disentangling by Factorisingcited by 614
  11. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  12. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
21 more
  1. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
  2. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  3. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  4. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  5. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  6. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  7. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
  8. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  9. 2020Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learningcited by 71
  10. 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
  11. 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
  12. 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
  13. 2019Transferable Contrastive Network for Generalized Zero-Shot Learningcited by 64
  14. 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
  15. 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
  16. 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
  17. 2017Generating Visual Representations for Zero-Shot Classificationcited by 37
  18. 2021Dual Progressive Prototype Network for Generalized Zero-Shot Learningcited by 26
  19. 2021Task Aligned Generative Meta-learning for Zero-shot Learningcited by 19
  20. 2021Mitigating Generation Shifts for Generalized Zero-Shot Learningcited by 13
  21. 2021Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learningcited by 3

Built on by

Not cited yet.