mlsanityData to 13 Oct 2026

Absolute Zero-Shot Learning

arXiv 2202.11319 ↗First posted 23 Feb 2022cs.CV cs.CR cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Considering the increasing concerns about data copyright and privacy issues, we present a novel Absolute Zero-Shot Learning (AZSL) paradigm, i.e., training a classifier with zero real data. The key innovation is to involve a teacher model as the data safeguard to guide the AZSL model training without data leaking. The AZSL model consists of a generator and student network, which can achieve date-free knowledge transfer while maintaining the performance of the teacher network. We investigate `black-box' and `white-box' scenarios in AZSL task as different levels of model security. Besides, we also provide discussion of teacher model in both inductive and transductive settings. Despite embarrassingly simple implementations and data-missing disadvantages, our AZSL framework can retain state-of-the-art ZSL and GZSL performance under the `white-box' scenario. Extensive qualitative and quantitative analysis also demonstrates promising results when deploying the model under `black-box' scenario.

Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 35 of its 59 references that are in the map. First posted on arXiv 23 Feb 2022.

Builds on

35 of 59 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
  5. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,470
  6. 2019Deep Leakage from Gradientscited by 1,017
  7. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
  8. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 517
  9. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 420
  10. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  11. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  12. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
23 more
  1. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  2. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  3. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  4. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  5. 2021Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learningcited by 130
  6. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
  7. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  8. 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
  9. 2018Multi-modal Cycle-consistent Generalized Zero-Shot Learningcited by 87
  10. 2020Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learningcited by 71
  11. 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
  12. 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
  13. 2020Wasserstein Contrastive Representation Distillationcited by 63
  14. 2015Transductive Multi-view Zero-Shot Learningcited by 53
  15. 2018Transductive Unbiased Embedding for Zero-Shot Learningcited by 44
  16. 2017Iterative Machine Teachingcited by 40
  17. 2014Zero Shot Recognition with Unreliable Attributescited by 39
  18. 2018Preserving Semantic Relations for Zero-Shot Learningcited by 35
  19. 2018Progressive Ensemble Networks for Zero-Shot Recognitioncited by 23
  20. 2020Computation-Efficient Knowledge Distillation via Uncertainty-Aware Mixupcited by 22
  21. 2017From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesiscited by 21
  22. 2018Towards Effective Deep Embedding for Zero-Shot Learningcited by 19
  23. 2020Generative Model-driven Structure Aligning Discriminative Embeddings for Transductive Zero-shot Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learningcited by 10
  2. 2025Asynchronous Personalized Federated Learning through Global Memorizationcited by 0