mlsanityData to 14 Oct 2026

Sentinel-Guided Zero-Shot Learning: A Collaborative Paradigm without Real Data Exposure

arXiv 2403.09363 ↗First posted 14 Mar 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

With increasing concerns over data privacy and model copyrights, especially in the context of collaborations between AI service providers and data owners, an innovative SG-ZSL paradigm is proposed in this work. SG-ZSL is designed to foster efficient collaboration without the need to exchange models or sensitive data. It consists of a teacher model, a student model and a generator that links both model entities. The teacher model serves as a sentinel on behalf of the data owner, replacing real data, to guide the student model at the AI service provider's end during training. Considering the disparity of knowledge space between the teacher and student, we introduce two variants of the teacher model: the omniscient and the quasi-omniscient teachers. Under these teachers' guidance, the student model seeks to match the teacher model's performance and explores domains that the teacher has not covered. To trade off between privacy and performance, we further introduce two distinct security-level training protocols: white-box and black-box, enhancing the paradigm's adaptability. Despite the inherent challenges of real data absence in the SG-ZSL paradigm, it consistently outperforms in ZSL and GZSL tasks, notably in the white-box protocol. Our comprehensive evaluation further attests to its robustness and efficiency across various setups, including stringent black-box training protocol.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 36 of its 72 references that are in the map. First posted on arXiv 14 Mar 2024.

Builds on

36 of 72 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  4. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
  5. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
  6. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
  7. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 383
  8. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  9. 2021Knowledge distillation: A good teacher is patient and consistentcited by 259
  10. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  11. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  12. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
24 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. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  5. 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
  6. 2022Automatic Clipping: Differentially Private Deep Learning Made Easier and Strongercited by 88
  7. 2018Multi-modal Cycle-consistent Generalized Zero-Shot Learningcited by 87
  8. 2020Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learningcited by 71
  9. 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
  10. 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
  11. 2015Transductive Multi-view Zero-Shot Learningcited by 53
  12. 2018Transductive Unbiased Embedding for Zero-Shot Learningcited by 44
  13. 2014Zero Shot Recognition with Unreliable Attributescited by 39
  14. 2021Student Network Learning via Evolutionary Knowledge Distillationcited by 30
  15. 2020Computation-Efficient Knowledge Distillation via Uncertainty-Aware Mixupcited by 22
  16. 2021FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumoniacited by 22
  17. 2017From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesiscited by 21
  18. 2022Robust Region Feature Synthesizer for Zero-Shot Object Detectioncited by 20
  19. 2022Hybrid Routing Transformer for Zero-Shot Learningcited by 20
  20. 2018Towards Effective Deep Embedding for Zero-Shot Learningcited by 19
  21. 2022Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edgescited by 12
  22. 2020Topology-aware Differential Privacy for Decentralized Image Classificationcited by 6
  23. 2020FedBoosting: Federated Learning with Gradient Protected Boosting for Text Recognitioncited by 6
  24. 2020Generative Model-driven Structure Aligning Discriminative Embeddings for Transductive Zero-shot Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025Rethinking Brain Tumor Segmentation from the Frequency Domain Perspectivecited by 9
  2. 2025TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiencycited by 8
  3. 2025FMDConv: Fast Multi-Attention Dynamic Convolution via Speed-Accuracy Trade-offcited by 1
  4. 2025Asynchronous Personalized Federated Learning through Global Memorizationcited by 0