mlsanityData to 14 Oct 2026

GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning

arXiv 2309.00923 ↗First posted 2 Sep 2023cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

This paper investigates a challenging problem of zero-shot learning in the multi-label scenario (MLZSL), wherein, the model is trained to recognize multiple unseen classes within a sample (e.g., an image) based on seen classes and auxiliary knowledge, e.g., semantic information. Existing methods usually resort to analyzing the relationship of various seen classes residing in a sample from the dimension of spatial or semantic characteristics, and transfer the learned model to unseen ones. But they ignore the effective integration of local and global features. That is, in the process of inferring unseen classes, global features represent the principal direction of the image in the feature space, while local features should maintain uniqueness within a certain range. This integrated neglect will make the model lose its grasp of the main components of the image. Relying only on the local existence of seen classes during the inference stage introduces unavoidable bias. In this paper, we propose a novel and effective group bi-enhancement framework for MLZSL, dubbed GBE-MLZSL, to fully make use of such properties and enable a more accurate and robust visual-semantic projection. Specifically, we split the feature maps into several feature groups, of which each feature group can be trained independently with the Local Information Distinguishing Module (LID) to ensure uniqueness. Meanwhile, a Global Enhancement Module (GEM) is designed to preserve the principal direction. Besides, a static graph structure is designed to construct the correlation of local features. Experiments on large-scale MLZSL benchmark datasets NUS-WIDE and Open-Images-v4 demonstrate that the proposed GBE-MLZSL outperforms other state-of-the-art methods with large margins.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 56 of its 83 references that are in the map. First posted on arXiv 2 Sep 2023.

Builds on

56 of 83 references.

References · 56

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Going Deeper with Convolutionscited by 4,241
  4. 2019Multi-Label Image Recognition with Graph Convolutional Networkscited by 322
  5. 2018Bilinear Attention Networkscited by 280
  6. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 255
  7. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  8. 2016CNN-RNN: A Unified Framework for Multi-label Image Classificationcited by 190
  9. 2015Label-Embedding for Image Classificationcited by 165
  10. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  11. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  12. 2016Latent Embeddings for Zero-shot Classificationcited by 129
38 more
  1. 2019Learning a Deep ConvNet for Multi-label Classification with Partial Labelscited by 124
  2. 2017Learning From Noisy Large-Scale Datasets With Minimal Supervisioncited by 115
  3. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  4. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  5. 2021Multi-Label Learning from Single Positive Labelscited by 81
  6. 2017Multi-Label Zero-Shot Learning with Structured Knowledge Graphscited by 72
  7. 2013Large-scale Multi-label Learning with Missing Labelscited by 58
  8. 2020Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognitioncited by 50
  9. 2013Deep Convolutional Ranking for Multilabel Image Annotationcited by 47
  10. 2015Ridge Regression, Hubness, and Zero-Shot Learningcited by 44
  11. 2015Zero-Shot Learning via Joint Latent Similarity Embeddingcited by 39
  12. 2022Large Loss Matters in Weakly Supervised Multi-Label Classificationcited by 38
  13. 2022Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learningcited by 37
  14. 2020A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansioncited by 31
  15. 2023SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detectioncited by 28
  16. 2021Discriminative Region-based Multi-Label Zero-Shot Learningcited by 27
  17. 2021Semantic Diversity Learning for Zero-Shot Multi-label Classificationcited by 24
  18. 2021Personalized Federated Learning with Contextualized Generalizationcited by 23
  19. 2016Multi-Cue Zero-Shot Learning with Strong Supervisioncited by 22
  20. 2016Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classificationcited by 22
  21. 2016Fast Zero-Shot Image Taggingcited by 21
  22. 2021MlTr: Multi-label Classification with Transformercited by 21
  23. 2022Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attentioncited by 21
  24. 2019AMS-SFE: Towards an Alignment of Manifold Structures via Semantic Feature Expansion for Zero-shot Learningcited by 19
  25. 2019Adaptive Adjustment with Semantic Feature Space for Zero-Shot Recognitioncited by 18
  26. 2019Position-Aware Convolutional Networks for Traffic Predictioncited by 18
  27. 2022Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotationscited by 17
  28. 2022Exploring Optimal Substructure for Out-of-distribution Generalization via Feature-targeted Model Pruningcited by 17
  29. 2023Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learningcited by 17
  30. 2023DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learningcited by 17
  31. 2021Learning Robust Visual-semantic Mapping for Zero-shot Learningcited by 16
  32. 2022Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruningcited by 16
  33. 2019EE-AE: An Exclusivity Enhanced Unsupervised Feature Learning Approachcited by 15
  34. 2023CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenariocited by 15
  35. 2022Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Networkcited by 14
  36. 2021Mitigating Generation Shifts for Generalized Zero-Shot Learningcited by 13
  37. 2023Arena: A Learning-based Synchronization Scheme for Hierarchical Federated Learning--Technical Reportcited by 13
  38. 2019Collaboration based Multi-Label Learningcited by 11

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 5; 2025: 1.

8 papers.

  1. 2024Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognitioncited by 19
  2. 2024Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognitioncited by 13
  3. 2024Fine-Grained Zero-Shot Learning: Advances, Challenges, and Prospectscited by 12
  4. 2023Attribute-Aware Representation Rectification for Generalized Zero-Shot Learningcited by 6
  5. 2024On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Surveycited by 5
  6. 2023ParsNets: A Parsimonious Orthogonal and Low-Rank Linear Networks for Zero-Shot Learningcited by 4
  7. 2024Dual Expert Distillation Network for Generalized Zero-Shot Learningcited by 4
  8. 2025FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Datacited by 0