mlsanityData to 7 Oct 2026

Attribute-Modulated Generative Meta Learning for Zero-Shot Classification

arXiv 2104.10857 ↗First posted 22 Apr 2021cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to semantically related unseen classes, which are absent during training. The promising strategies for ZSL are to synthesize visual features of unseen classes conditioned on semantic side information and to incorporate meta-learning to eliminate the model's inherent bias towards seen classes. While existing meta generative approaches pursue a common model shared across task distributions, we aim to construct a generative network adaptive to task characteristics. To this end, we propose an Attribute-Modulated generAtive meta-model for Zero-shot learning (AMAZ). Our model consists of an attribute-aware modulation network, an attribute-augmented generative network, and an attribute-weighted classifier. Given unseen classes, the modulation network adaptively modulates the generator by applying task-specific transformations so that the generative network can adapt to highly diverse tasks. The weighted classifier utilizes the data quality to enhance the training procedure, further improving the model performance. Our empirical evaluations on four widely-used benchmarks show that AMAZ outperforms state-of-the-art methods by 3.8% and 3.1% in ZSL and generalized ZSL settings, respectively, demonstrating the superiority of our method. Our experiments on a zero-shot image retrieval task show AMAZ's ability to synthesize instances that portray real visual characteristics.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 43 of its 77 references that are in the map. First posted on arXiv 22 Apr 2021.

Builds on

43 of 77 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  5. 2018Self-Attention Generative Adversarial Networkscited by 809
  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. 2020A Comprehensive Survey of Neural Architecture Search: Challenges and Solutionscited by 253
  9. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  10. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  11. 2017Modulating early visual processing by languagecited by 167
  12. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
31 more
  1. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  2. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  3. 2016Latent Embeddings for Zero-shot Classificationcited by 129
  4. 2020Meta-Transfer Learning for Zero-Shot Super-Resolutioncited by 116
  5. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  6. 2019Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulationcited by 103
  7. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  8. 2018Multi-modal Cycle-consistent Generalized Zero-Shot Learningcited by 87
  9. 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
  10. 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
  11. 2020Zero-Shot Cross-Lingual Transfer with Meta Learningcited by 66
  12. 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
  13. 2015Transductive Multi-view Zero-Shot Learningcited by 53
  14. 2015Ridge Regression, Hubness, and Zero-Shot Learningcited by 44
  15. 2020Global Wheat Head Detection (GWHD) dataset: a large and diverse dataset of high resolution RGB labelled images to develop and benchmark wheat head detection methodscited by 42
  16. 2017A Simple Exponential Family Framework for Zero-Shot Learningcited by 38
  17. 2019Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learningcited by 38
  18. 2019Transductive Zero-Shot Learning with Visual Structure Constraintcited by 36
  19. 2020Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognitioncited by 34
  20. 2019TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learningcited by 32
  21. 2020Attribute Propagation Network for Graph Zero-shot Learningcited by 29
  22. 2020Diversity inducing Information Bottleneck in Model Ensemblescited by 27
  23. 2019Zero-Shot Task Transfercited by 26
  24. 2018Progressive Ensemble Networks for Zero-Shot Recognitioncited by 23
  25. 2017Zero-Shot Learning via Class-Conditioned Deep Generative Modelscited by 21
  26. 2018Generalized Zero-Shot Recognition based on Visually Semantic Embeddingcited by 19
  27. 2021Task Aligned Generative Meta-learning for Zero-shot Learningcited by 19
  28. 2019Deep Object Co-segmentation via Spatial-Semantic Network Modulationcited by 15
  29. 2018Zero-Shot Kernel Learningcited by 11
  30. 2020Simple and effective localized attribute representations for zero-shot learningcited by 7
  31. 2018Imagination Based Sample Construction for Zero-Shot Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 7; 2023: 1.

8 papers.

  1. 2022SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classificationcited by 34
  2. 2022Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attentioncited by 21
  3. 2022GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learningcited by 12
  4. 2023Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learningcited by 11
  5. 2022Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learningcited by 4
  6. 2022Disentangled and Side-aware Unsupervised Domain Adaptation for Cross-dataset Subjective Tinnitus Diagnosiscited by 3
  7. 2022Side-aware Meta-Learning for Cross-Dataset Listener Diagnosis with Subjective Tinnituscited by 2
  8. 2022MetaComp: Learning to Adapt for Online Depth Completioncited by 0