mlsanityData to 7 Oct 2026

Zero-Shot Learning by Harnessing Adversarial Samples

arXiv 2308.00313 ↗First posted 1 Aug 2023cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

Zero-Shot Learning (ZSL) aims to recognize unseen classes by generalizing the knowledge, i.e., visual and semantic relationships, obtained from seen classes, where image augmentation techniques are commonly applied to improve the generalization ability of a model. However, this approach can also cause adverse effects on ZSL since the conventional augmentation techniques that solely depend on single-label supervision is not able to maintain semantic information and result in the semantic distortion issue consequently. In other words, image argumentation may falsify the semantic (e.g., attribute) information of an image. To take the advantage of image augmentations while mitigating the semantic distortion issue, we propose a novel ZSL approach by Harnessing Adversarial Samples (HAS). HAS advances ZSL through adversarial training which takes into account three crucial aspects: (1) robust generation by enforcing augmentations to be similar to negative classes, while maintaining correct labels, (2) reliable generation by introducing a latent space constraint to avert significant deviations from the original data manifold, and (3) diverse generation by incorporating attribute-based perturbation by adjusting images according to each semantic attribute's localization. Through comprehensive experiments on three prominent zero-shot benchmark datasets, we demonstrate the effectiveness of our adversarial samples approach in both ZSL and Generalized Zero-Shot Learning (GZSL) scenarios. Our source code is available at https://github.com/uqzhichen/HASZSL.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 37 of its 51 references that are in the map. First posted on arXiv 1 Aug 2023.

Builds on

37 of 51 references.

References · 37

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  5. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  6. 2017Random Erasing Data Augmentationcited by 1,235
  7. 2018Robustness May Be at Odds with Accuracycited by 873
  8. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  9. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  10. 2019Adversarial Examples Improve Image Recognitioncited by 283
  11. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  12. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
25 more
  1. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  2. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  3. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  4. 2020Understanding and Mitigating the Tradeoff Between Robustness and Accuracycited by 148
  5. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  6. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  7. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  8. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  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. 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
  12. 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
  13. 2019Transferable Contrastive Network for Generalized Zero-Shot Learningcited by 64
  14. 2019Semantic-Guided Multi-Attention Localization for Zero-Shot Learningcited by 58
  15. 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
  16. 2020SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Datacited by 56
  17. 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
  18. 2020Invertible Zero-Shot Recognition Flowscited by 48
  19. 2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
  20. 2021Pyramid Adversarial Training Improves ViT Performancecited by 39
  21. 2020Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patchescited by 27
  22. 2019CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Languagecited by 23
  23. 2017Zero-Shot Learning via Class-Conditioned Deep Generative Modelscited by 21
  24. 2021Mitigating Generation Shifts for Generalized Zero-Shot Learningcited by 13
  25. 2022GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learningcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 9; 2026: 6.

24 papers.

Sort:

By area:

  1. 2024Universal Adversarial Perturbations for Vision-Language Pre-trained Modelscited by 31
  2. 2025Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptationcited by 7
  3. 2023Attribute-Aware Representation Rectification for Generalized Zero-Shot Learningcited by 6
  4. 2025SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learningcited by 6
  5. 2024On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Surveycited by 5
  6. 2024Continual Learning Improves Zero-Shot Action Recognitioncited by 5
  7. 2024Is Less More? Exploring Token Condensation as Training-free Test-time Adaptationcited by 5
  8. 2024Zero-Shot Automatic Annotation and Instance Segmentation using LLM-Generated Datasets: Eliminating Field Imaging and Manual Annotation for Deep Learning Model Developmentcited by 5
  9. 2025GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencodercited by 5
  10. 2024Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learningcited by 4
  11. 2025Distributed Zero-Shot Learning for Visual Recognitioncited by 3
  12. 2024ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learningcited by 2
12 more
  1. 2025Is Temporal Prompting All We Need For Limited Labeled Action Recognition?cited by 2
  2. 2026Accelerating Multimodal Large Language Models with Prior-Corrected Token Reductioncited by 2
  3. 2026Spectral Evolution-Guided Token Pruning in Multimodal Large Language Modelscited by 1
  4. 2024High-Discriminative Attribute Feature Learning for Generalized Zero-Shot Learningcited by 0
  5. 2025Class Similarity-Based Multimodal Classification under Heterogeneous Category Setscited by 0
  6. 2025Multi-Granularity Mutual Refinement Network for Zero-Shot Learningcited by 0
  7. 2025Fine-Grained Zero-Shot Learning with Attribute-Centric Representationscited by 0
  8. 2025Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilitiescited by 0
  9. 2026Hierarchical Refinement of Universal Multimodal Attacks on Vision-Language Modelscited by 0
  10. 2026PMCE: Probabilistic Multi-Granularity Semantics with Caption-Guided Enhancement for Few-Shot Learningcited by 0
  11. 2026StomataSeg: Semi-Supervised Instance Segmentation for Sorghum Stomatal Componentscited by 0
  12. 2026Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual Cuescited by 0