mlsanityData to 7 Oct 2026

Disentangling Semantic-to-visual Confusion for Zero-shot Learning

arXiv 2106.08605 ↗First posted 16 Jun 2021cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Using generative models to synthesize visual features from semantic distribution is one of the most popular solutions to ZSL image classification in recent years. The triplet loss (TL) is popularly used to generate realistic visual distributions from semantics by automatically searching discriminative representations. However, the traditional TL cannot search reliable unseen disentangled representations due to the unavailability of unseen classes in ZSL. To alleviate this drawback, we propose in this work a multi-modal triplet loss (MMTL) which utilizes multimodal information to search a disentangled representation space. As such, all classes can interplay which can benefit learning disentangled class representations in the searched space. Furthermore, we develop a novel model called Disentangling Class Representation Generative Adversarial Network (DCR-GAN) focusing on exploiting the disentangled representations in training, feature synthesis, and final recognition stages. Benefiting from the disentangled representations, DCR-GAN could fit a more realistic distribution over both seen and unseen features. Extensive experiments show that our proposed model can lead to superior performance to the state-of-the-arts on four benchmark datasets. Our code is available at https://github.com/FouriYe/DCRGAN-TMM.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 36 of its 62 references that are in the map. First posted on arXiv 16 Jun 2021.

Builds on

36 of 62 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  4. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  5. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
  6. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  7. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  8. 2015Label-Embedding for Image Classificationcited by 164
  9. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  10. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  11. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  12. 2016Latent Embeddings for Zero-shot Classificationcited by 129
24 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. 2018Multi-modal Cycle-consistent Generalized Zero-Shot Learningcited by 87
  4. 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74
  5. 2020Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learningcited by 71
  6. 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
  7. 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
  8. 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
  9. 2015Ridge Regression, Hubness, and Zero-Shot Learningcited by 44
  10. 2015Zero-Shot Learning via Joint Latent Similarity Embeddingcited by 39
  11. 2018Preserving Semantic Relations for Zero-Shot Learningcited by 35
  12. 2019In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillationcited by 34
  13. 2016Gaze Embeddings for Zero-Shot Image Classificationcited by 25
  14. 2018Discriminative Learning of Latent Features for Zero-Shot Recognitioncited by 24
  15. 2020Multi-Domain Multi-Task Rehearsal for Lifelong Learningcited by 24
  16. 2017From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesiscited by 21
  17. 2019Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learningcited by 20
  18. 2016Zero-Shot Hashing via Transferring Supervised Knowledgecited by 15
  19. 2018Learning Class Prototypes via Structure Alignment for Zero-Shot Recognitioncited by 14
  20. 2019Alleviating Feature Confusion for Generative Zero-shot Learningcited by 10
  21. 2018Selective Zero-Shot Classification with Augmented Attributescited by 9
  22. 2021Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learningcited by 8
  23. 2019SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learningcited by 6
  24. 2017Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 1; 2025: 3; 2026: 1.

11 papers.

  1. 2023Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Trackingcited by 10
  2. 2024ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learningcited by 10
  3. 2022Rebalanced Zero-shot Learningcited by 8
  4. 2022Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learningcited by 4
  5. 2023Open-Pose 3D Zero-Shot Learning: Benchmark and Challengescited by 4
  6. 2023Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learningcited by 3
  7. 2025Distributed Zero-Shot Learning for Visual Recognitioncited by 3
  8. 2023Instance Adaptive Prototypical Contrastive Embedding for Generalized Zero Shot Learningcited by 0
  9. 2025GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Modelscited by 0
  10. 2025Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilitiescited by 0
  11. 2026ZeroDiff++: Substantial Unseen Visual-semantic Correlation in Zero-shot Learningcited by 0